© 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. 127701
    Prev
    Next
    INDEX
    Explanations

    other organizations, own designs

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

    Estimated Illnesses

    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
     qq
    0.50
     q
    0.47
    aset
    0.47
     RCA
    0.47
     GDP
    0.47
     H
    0.47
     QD
    0.46
    <0x9B>
    0.45
    怕
    0.45
     dotted
    0.44
    POSITIVE LOGITS
    вано
    0.52
    Speech
    0.50
    Jest
    0.48
    ূন্য
    0.45
    മുണ്ട്
    0.44
    jonen
    0.44
    ளின்
    0.44
    Dealer
    0.44
    Transportation
    0.43
    Flexible
    0.43
    Activations Density 0.001%

    No Known Activations