© 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. 5267
    Prev
    Next
    INDEX
    Explanations

    Redux observable, connected

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

    useReducer, reducer, useContext

    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
    SourceRequest
    0.53
    ;');
    0.51
     IOException
    0.46
    ৩৬
    0.45
    clientsdetails
    0.44
    Silent
    0.44
     যাওয়ার
    0.44
    矨
    0.43
    າມາດ
    0.42
    设定
    0.42
    POSITIVE LOGITS
     parable
    0.48
     conund
    0.46
     dall
    0.44
     dan
    0.44
    adl
    0.44
    })(
    0.43
     sart
    0.43
    attva
    0.43
    奶奶
    0.43
     nadi
    0.42
    Activations Density 0.000%

    No Known Activations