© 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. 169889
    Prev
    Next
    INDEX
    Explanations

    claims and responsibility

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

    service workers

    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
    setPreferredSize
    0.49
     ም
    0.48
     聞い
    0.45
     pond
    0.45
     outcast
    0.44
     ocul
    0.44
    correspond
    0.43
     fundraiser
    0.43
    ței
    0.42
     干
    0.42
    POSITIVE LOGITS
     lysates
    0.54
     эффект
    0.53
    ا
    0.51
     nipples
    0.50
     chảy
    0.49
     effetto
    0.49
     পোশাক
    0.48
     tights
    0.48
     effets
    0.47
     nanotubes
    0.46
    Activations Density 0.000%

    No Known Activations