© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15018
    Prev
    Next
    INDEX
    Explanations

    Bangkok, Ponto, transfection, uninstall, Villanova

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

    words or concepts related to software uninstallation and installation processes.

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

    This neuron detects capitalized proper nouns.

    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
    ization
    -2.64
     ใน
    -2.42
    ться
    -2.42
     Ensuring
    -2.41
     unsere
    -2.41
     เมื่อ
    -2.36
    n
    -2.33
     عندما
    -2.30
    each
    -2.28
    一些
    -2.25
    POSITIVE LOGITS
    的吗
    3.06
    鞮
    2.61
    汌
    2.27
    сті
    2.25
    といふ
    2.23
    的那种
    2.22
    ⸒
    2.22
     wit
    2.20
    <td>
    2.20
    着一个
    2.19
    Activations Density 0.025%

    No Known Activations