© 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. 10931
    Prev
    Next
    INDEX
    Explanations

    and other

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

    and connecting items

    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
     Dieser
    0.48
     حصول
    0.48
    ،
    0.45
     Though
    0.45
    、
    0.44
     meliputi
    0.42
     çarp
    0.41
     وم
    0.41
     হওয়ায়
    0.40
     varier
    0.40
    POSITIVE LOGITS
     there
    0.54
     it
    0.52
    There
    0.52
    También
    0.50
    feeling
    0.50
    Mapa
    0.50
     also
    0.50
     accidentally
    0.49
    M
    0.49
    ੜ
    0.48
    Activations Density 0.008%

    No Known Activations