© 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. 135108
    Prev
    Next
    INDEX
    Explanations

    Google data services and alternatives

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

    non-ultra-pasteurized

    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
     explot
    0.50
    ז
    0.47
    ал
    0.47
    קט
    0.47
    ץ
    0.46
    ᅵ
    0.45
    טי
    0.45
    ρι
    0.45
    زي
    0.44
     exploiting
    0.44
    POSITIVE LOGITS
     ദിവസ
    0.48
     Trouble
    0.47
     Mabel
    0.47
     Acceptance
    0.43
     Roanoke
    0.43
     Strokes
    0.43
     Gnome
    0.43
     Nautilus
    0.42
     अखबार
    0.42
     Seph
    0.42
    Activations Density 0.001%

    No Known Activations