© 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. 243249
    Prev
    Next
    INDEX
    Explanations

    website, subscriptions, user, earth, vaccinate, product

    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
    Religion
    0.48
    ())
    0.47
     usc
    0.47
    Reaction
    0.45
    <unused976>
    0.44
    <unused740>
    0.44
     इत्या
    0.43
     Sensitivity
    0.42
     Lassen
    0.42
    𝐜
    0.42
    POSITIVE LOGITS
    ᱗
    0.52
     तत्कालीन
    0.46
    右
    0.46
    ７
    0.45
    時代の
    0.45
    ６
    0.45
     tòa
    0.45
    她
    0.45
    뮐
    0.45
    当時
    0.44
    Activations Density 0.001%

    No Known Activations