© 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. 99311
    Prev
    Next
    INDEX
    Explanations

    cost, bottle, lyrics, courts, consultants

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

    validation and voltage

    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
    Per
    0.46
     specialist
    0.45
     (=
    0.43
    ologist
    0.42
    ENT
    0.41
    ent
    0.41
     quad
    0.41
    レンタル
    0.40
     ∣
    0.40
     برش
    0.40
    POSITIVE LOGITS
     상태
    0.59
     않은
    0.51
     retval
    0.49
     REACTIONS
    0.46
     tarihi
    0.46
     atuais
    0.46
     statuses
    0.46
     actuales
    0.46
    кара
    0.46
    ඨ
    0.45
    Activations Density 0.002%

    No Known Activations