© 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. 206843
    Prev
    Next
    INDEX
    Explanations

    roles and stated actions

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

    operate in shadows or early 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
     Cnemidophorus
    0.55
     ದಿ
    0.55
    <unused79>
    0.52
     فاس
    0.52
     ខ
    0.51
     клиента
    0.51
    အချိန်
    0.51
     İyi
    0.51
     tuss
    0.50
     Пользова
    0.50
    POSITIVE LOGITS
    CA
    0.53
    IC
    0.52
    p
    0.52
    Y
    0.52
    ES
    0.49
    IT
    0.48
    Coconut
    0.47
    </td>
    0.46
    FINED
    0.46
    RO
    0.45
    Activations Density 0.001%

    No Known Activations