© 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. 111546
    Prev
    Next
    INDEX
    Explanations

    free, recognised, proper

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

    weights, pads, bases, codes

    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
    𝙥
    0.45
     lawmakers
    0.44
     speculating
    0.43
     lorsque
    0.43
    ifiez
    0.43
    ்ச்ச
    0.42
    ildiği
    0.41
    sap
    0.41
    他对
    0.40
     satisfactory
    0.40
    POSITIVE LOGITS
     embossed
    0.50
     JOY
    0.46
    BZ
    0.42
    з
    0.42
    IndexArray
    0.42
     EMB
    0.41
     அல்ல
    0.41
     Emb
    0.41
     emb
    0.40
     обме
    0.39
    Activations Density 0.000%

    No Known Activations