© 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. 110771
    Prev
    Next
    INDEX
    Explanations

    based on

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

    based on neurological correlates

    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
     externos
    0.53
     进入
    0.52
     activos
    0.50
    낍
    0.47
     leyes
    0.47
    র্ধ্ব
    0.46
     जियो
    0.44
     aktywn
    0.44
     তন্ত্র
    0.44
     negativos
    0.44
    POSITIVE LOGITS
    s
    0.55
     Confidential
    0.53
    atm
    0.51
    <0xAF>
    0.50
     Based
    0.49
     based
    0.48
     famous
    0.47
     Lik
    0.47
    on
    0.47
    ого
    0.46
    Activations Density 0.001%

    No Known Activations