© 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. 10-GEMMASCOPE-RES-131K
    7. 677
    Prev
    Next
    INDEX
    Explanations

    laid-back

    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_10/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
    </b>
    -2.53
     It
    -2.11
     *
    -2.03
    ↵
    -2.02
     Even
    -1.98
     With
    -1.97
    In
    -1.92
     When
    -1.92
    I
    -1.91
    </i>
    -1.85
    POSITIVE LOGITS
    珰
    2.30
    
    2.23
    ⢓
    2.23
    鸶
    2.22
     dezelve
    2.22
    夲
    2.20
     hunne
    2.19
     klim
    2.11
     绒
    2.09
     westfalen
    2.06
    Activations Density 0.010%

    No Known Activations