© 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. 219865
    Prev
    Next
    INDEX
    Explanations

    use and works

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

    custom code action

    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
     bellissimo
    0.55
    மில்லை
    0.55
    எல்
    0.55
     Sì
    0.54
     Tapat
    0.54
     Đúng
    0.54
     சாதன
    0.53
    ◟
    0.52
    <unused72>
    0.52
    瞽
    0.52
    POSITIVE LOGITS
    가
    0.56
     use
    0.51
    MOS
    0.51
     molecule
    0.49
    asia
    0.45
    (
    0.45
    </h2>
    0.45
    use
    0.45
     molecules
    0.44
     troops
    0.44
    Activations Density 0.000%

    No Known Activations