© 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. 34-GEMMASCOPE-RES-131K
    7. 110566
    Prev
    Next
    INDEX
    Explanations

    case details

    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_34/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
    iddhar
    -1.01
    Upgradeable
    -0.99
    हर
    -0.97
    髴
    -0.95
     ярма
    -0.94
    uyucu
    -0.91
     Montréal
    -0.90
    ffè
    -0.89
    }$,
    -0.88
    sometimes
    -0.88
    POSITIVE LOGITS
     evidence
    1.38
     motive
    1.38
    motive
    1.28
     могло
    1.24
     plausible
    1.24
     knew
    1.23
     other
    1.23
     pudo
    1.23
     alibi
    1.23
     key
    1.18
    Activations Density 0.028%

    No Known Activations