© 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. 12378
    Prev
    Next
    INDEX
    Explanations

    including or excluding parentheticals

    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
    AutoModerator
    -1.06
    Ӕ
    -1.06
    Jesmyn
    -0.98
    ią
    -0.98
    ovka
    -0.95
    äder
    -0.93
     náš
    -0.90
    そして
    -0.90
     nightclub
    -0.89
    ׂ
    -0.89
    POSITIVE LOGITS
     including
    1.24
     which
    1.23
    clud
    1.09
    .
    1.00
     necessary
    0.98
     required
    0.96
     inclusief
    0.94
     at
    0.94
     needed
    0.94
     excluding
    0.93
    Activations Density 0.075%

    No Known Activations