© 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. 30834
    Prev
    Next
    INDEX
    Explanations

    calls to you

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

    installing libraries like transformers

    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
     от
    0.48
     при
    0.43
     под
    0.42
    rift
    0.42
     ล
    0.42
    c
    0.42
     தென்
    0.41
     еле
    0.41
     ティ
    0.41
     ス
    0.40
    POSITIVE LOGITS
     carers
    0.46
    Eligibility
    0.45
    siniz
    0.44
     Eligibility
    0.44
    :
    0.44
     psychologists
    0.43
    ısınız
    0.43
     candidates
    0.42
     economists
    0.42
     maatau
    0.42
    Activations Density 0.000%

    No Known Activations