© 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. 95509
    Prev
    Next
    INDEX
    Explanations

    departures days

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

    defining concepts and roles

    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
    uan
    0.45
    </h2>
    0.44
    AAA
    0.44
    allele
    0.44
    det
    0.43
    IEEE
    0.43
     Type
    0.43
    RET
    0.43
    AQP
    0.43
    ENT
    0.42
    POSITIVE LOGITS
     internationaux
    0.55
    ထိ
    0.53
    isés
    0.52
     vendeurs
    0.52
    ３
    0.52
     সঙ্ক
    0.50
     encouraged
    0.50
    ᓱ
    0.50
     αγο
    0.50
    ulièrement
    0.49
    Activations Density 0.000%

    No Known Activations