© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 84057
    Prev
    Next
    INDEX
    Explanations

    defines meanings or origins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    íč
    -1.19
    áček
    -1.02
    Lot
    -1.01
    ceptable
    -0.99
    Tony
    -0.97
     موارد
    -0.96
     такі
    -0.95
    人気
    -0.92
    Jeffrey
    -0.91
    นี่
    -0.91
    POSITIVE LOGITS
    ことから
    1.12
     diharapkan
    1.11
     our
    1.05
    İŞ
    0.99
    他想
    0.96
     nostru
    0.95
     также
    0.95
     both
    0.93
     enligt
    0.93
    wiąz
    0.92
    Activations Density 0.040%

    No Known Activations