© 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. 242723
    Prev
    Next
    INDEX
    Explanations

    role model or claims

    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
     overwhelmingly
    0.47
     everybody
    0.45
     everyone
    0.45
     mall
    0.44
    발
    0.44
    <h3>
    0.43
    summary
    0.43
     malls
    0.43
    যখন
    0.43
     instinctively
    0.43
    POSITIVE LOGITS
     групи
    0.47
     фаразлау
    0.46
    等は
    0.45
     ഊ
    0.45
    访
    0.44
     دوب
    0.44
     дві
    0.44
     рэгістрацыі
    0.43
     የተለያዩ
    0.43
     gru
    0.43
    Activations Density 0.000%

    No Known Activations