© 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. 209656
    Prev
    Next
    INDEX
    Explanations

    targeted therapy

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

    specializing in role

    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
    м
    0.54
    م
    0.48
    د
    0.47
    .
    0.47
    he
    0.43
    projects
    0.43
    т
    0.42
    <0x89>
    0.42
    س
    0.41
     capital
    0.41
    POSITIVE LOGITS
     smuggled
    0.48
     ఎలాంటి
    0.47
     hatched
    0.45
     natthi
    0.45
     shattered
    0.45
     hiding
    0.44
     arrested
    0.43
     नीचे
    0.43
    न्ड
    0.43
    findOne
    0.43
    Activations Density 0.001%

    No Known Activations