© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 135687
    Prev
    Next
    INDEX
    Explanations

    almost / nearly

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

    likely harder to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     अगेन
    0.49
     ასევე
    0.46
    िवेशन
    0.46
    udni
    0.45
    憸
    0.45
     yine
    0.44
    ㄈ
    0.44
    🕺
    0.44
    滪
    0.44
     أيضاً
    0.43
    POSITIVE LOGITS
     eigen
    0.42
    ほぼ
    0.41
     handled
    0.40
     object
    0.40
     almost
    0.39
     casi
    0.39
     practice
    0.38
    ほとんど
    0.38
     preparation
    0.38
    -
    0.38
    Activations Density 0.001%

    No Known Activations