© 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. 98987
    Prev
    Next
    INDEX
    Explanations

    professional, college, capped benefits

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

    AI performs

    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
    Sch
    0.47
    st
    0.46
    c
    0.46
     Schm
    0.45
    H
    0.45
    Gate
    0.44
     amenity
    0.44
    cum
    0.44
    end
    0.44
    Y
    0.44
    POSITIVE LOGITS
    ຜະລິດຕະພັນ
    0.56
    ல்லிய
    0.54
     வாங்க
    0.54
     différente
    0.54
    𝟘
    0.53
     различными
    0.52
    侢
    0.52
     discusión
    0.52
    𝟬
    0.52
     فريبي
    0.52
    Activations Density 0.001%

    No Known Activations