© 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. 29081
    Prev
    Next
    INDEX
    Explanations

    Warning notifications

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

    words followed by punctuation

    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
     Whelan
    0.54
    রির
    0.49
     іх
    0.47
     کوشش
    0.45
     дописа
    0.44
     MenuView
    0.44
     khúc
    0.44
    룹
    0.43
     immutable
    0.43
     الدراسي
    0.43
    POSITIVE LOGITS
    ft
    0.50
    cent
    0.48
    br
    0.48
    β
    0.48
    ECT
    0.45
     from
    0.45
     of
    0.45
     MEDIC
    0.45
    ps
    0.44
    ning
    0.43
    Activations Density 0.000%

    No Known Activations