© 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. 208239
    Prev
    Next
    INDEX
    Explanations

    join them

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

    claims processing

    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
     wesentlich
    0.55
    莞
    0.53
     deutlich
    0.52
     zusätz
    0.48
    EMANN
    0.47
     reichen
    0.47
     হাইড্রোক
    0.47
    疮
    0.46
     Bereich
    0.46
    CRIPTOR
    0.46
    POSITIVE LOGITS
     our
    0.46
     (
    0.45
     Sardar
    0.44
    antial
    0.43
     nj
    0.42
     Serious
    0.41
    ↵
    0.40
     themed
    0.40
    0.40
     RegExp
    0.39
    Activations Density 0.000%

    No Known Activations