© 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. 179425
    Prev
    Next
    INDEX
    Explanations

    offer accessible

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

    list of items

    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
    一行
    0.45
     বিভিন্ন
    0.42
    ED
    0.42
    Panel
    0.41
    ="<%=
    0.41
    UED
    0.40
    5
    0.40
    Nick
    0.38
    Liv
    0.38
    4
    0.37
    POSITIVE LOGITS
     वाक्या
    0.52
     meats
    0.49
     gamanam
    0.48
     школ
    0.48
     esiste
    0.47
     правой
    0.47
     médec
    0.45
    ഞ്ഞ
    0.45
     ઇ
    0.45
    foods
    0.44
    Activations Density 0.001%

    No Known Activations