© 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. 91392
    Prev
    Next
    INDEX
    Explanations

    you can find statistics

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

    adapted for

    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
     amat
    0.46
    这也是
    0.43
    ลูก
    0.42
     modelling
    0.42
    害怕
    0.42
    相
    0.41
     BoxFit
    0.41
     atrocious
    0.41
     آم
    0.40
    }());
    0.40
    POSITIVE LOGITS
    cipline
    0.46
     redesign
    0.45
     değişiklik
    0.45
    clim
    0.45
    changes
    0.44
     mobilize
    0.44
    ȱ
    0.43
    변경
    0.43
     Fielding
    0.43
     oxidize
    0.42
    Activations Density 0.001%

    No Known Activations