© 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. 139026
    Prev
    Next
    INDEX
    Explanations

    actions leading to next items

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

    avoiding good luck

    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
     havoc
    0.51
    що
    0.48
    勉強
    0.45
    щей
    0.45
     terlalu
    0.45
    ור
    0.44
     muncul
    0.44
    ﻭ
    0.44
    льше
    0.43
     хвата
    0.43
    POSITIVE LOGITS
    amino
    0.54
    VB
    0.54
    iking
    0.52
    reeting
    0.51
    immel
    0.50
    ürgen
    0.50
    ání
    0.49
    clipboard
    0.49
    ůj
    0.47
    ys
    0.47
    Activations Density 0.002%

    No Known Activations