© 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. 46487
    Prev
    Next
    INDEX
    Explanations

    a year, your skin, succeeded in

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

    stand up, sue the human race, avoiding eye

    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
    is
    0.49
    Agreement
    0.46
    mess
    0.44
    Passport
    0.43
    ↵
    0.43
    ins
    0.43
    order
    0.43
    ma
    0.43
    mer
    0.42
    paration
    0.42
    POSITIVE LOGITS
     danneggi
    0.49
     ০৯
    0.49
     ܘ
    0.46
     lLoginID
    0.46
     þat
    0.46
     scoperta
    0.46
     semifinal
    0.45
     detr
    0.45
    ниця
    0.45
     tagReport
    0.45
    Activations Density 0.000%

    No Known Activations