© 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. 12146
    Prev
    Next
    INDEX
    Explanations

    beginnings of events

    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
    sequently
    -1.22
    <bos>
    -1.17
     these
    -1.16
     ajuta
    -1.16
     diferite
    -1.15
     especially
    -1.10
    ⊂
    -1.09
    ご了承ください
    -1.02
     această
    -1.02
     pesso
    -1.02
    POSITIVE LOGITS
     with
    2.08
     on
    1.68
     by
    1.60
     at
    1.42
     from
    1.40
     сентября
    1.11
    躯
    1.06
     conva
    1.05
    氏が
    1.04
     inicio
    1.02
    Activations Density 0.041%

    No Known Activations