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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39182
    Prev
    Next
    INDEX
    Explanations

    forms of take

    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
    ↵
    -2.91
    r
    -2.66
    0
    -2.64
    n
    -2.44
    s
    -2.31
    "
    -2.31
    p
    -2.27
    |
    -2.25
    ri
    -2.25
    w
    -2.23
    POSITIVE LOGITS
     advantage
    2.78
     всѣ
    2.50
    摭
    2.41
    迓
    2.41
    絝
    2.38
    archiwizowane
    2.25
     raras
    2.13
    providedIn
    2.13
    
    2.11
    垌
    2.09
    Activations Density 0.052%

    No Known Activations