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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11562
    Prev
    Next
    INDEX
    Explanations

    people, places, or things

    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
    ところに
    -1.03
    になれば
    -0.98
     this
    -0.94
     gefallen
    -0.92
     ottobre
    -0.92
     Belgique
    -0.91
    zdo
    -0.91
    ülerin
    -0.89
    colha
    -0.87
    ٧
    -0.87
    POSITIVE LOGITS
    を
    1.30
    と
    1.00
    哂
    0.88
     biblia
    0.87
    vrier
    0.87
    で
    0.85
    が
    0.85
    ztes
    0.82
    は
    0.82
    <bos>
    0.82
    Activations Density 0.133%

    No Known Activations