© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67572
    Prev
    Next
    INDEX
    Explanations

    adhering to surfaces

    np_acts-logits-general · gemini-2.5-flash-lite

    phrases about objects sticking, adhering, or clinging to surfaces.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects words and word fragments related to adhesion or sticking (e.g., adhere, adhesion, stick, sticking).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     about
    -1.83
     块
    -1.64
    闢
    -1.46
     there
    -1.38
     解析
    -1.38
     级
    -1.35
     abuser
    -1.34
     框
    -1.34
     工具
    -1.32
    giatan
    -1.30
    POSITIVE LOGITS
    比如说
    1.55
    很少
    1.46
     underlines
    1.46
     underscores
    1.46
     санкт
    1.45
    小结
    1.44
    她说
    1.43
     obligado
    1.41
     pagado
    1.40
    取决
    1.38
    Activations Density 0.041%

    No Known Activations