© 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. 15214
    Prev
    Next
    INDEX
    Explanations

    preliminary

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

    initial or preliminary

    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
    ọt
    0.42
     ब्रह्मा
    0.41
    垠
    0.41
    城県
    0.40
    訟
    0.40
    বঙ্গের
    0.39
     மற
    0.39
    뚤
    0.39
    ága
    0.39
    狡
    0.39
    POSITIVE LOGITS
     preliminary
    1.52
     Preliminary
    1.37
     prelim
    1.33
     prelimin
    1.29
    初步
    1.28
    Preliminary
    1.26
     prélim
    1.19
     partial
    1.10
     предвари
    1.08
     preparatory
    1.08
    Activations Density 0.199%

    No Known Activations