© 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. 131629
    Prev
    Next
    INDEX
    Explanations

    Law, Saturday, Killer Strategy, Christians, ience

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

    avoiding trouble, distinguishing states

    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
     …
    0.47
     предупре
    0.46
     world
    0.45
     parle
    0.44
     monitor
    0.43
    co
    0.43
     absolutely
    0.43
    ga
    0.43
     оте
    0.43
     if
    0.42
    POSITIVE LOGITS
     कालीन
    0.52
    gewicht
    0.50
    铑
    0.49
    缡
    0.49
     Cyclic
    0.48
    GetLength
    0.46
    rž
    0.46
    ̀u
    0.45
    glm
    0.44
    ક્ર
    0.44
    Activations Density 0.007%

    No Known Activations