© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34147
    Prev
    Next
    INDEX
    Explanations

    map and words following it reveal Map-related concepts

    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
     ภาพถ่าย
    -2.83
    </em>
    -2.47
    銠
    -2.34
    齶
    -2.30
    
    -2.28
    🗹
    -2.27
    zaSy
    -2.22
     —
    -2.22
    ྅
    -2.20
    ,"
    -2.16
    POSITIVE LOGITS
    e
    3.97
    c
    3.67
    i
    3.28
    d
    2.81
    ar
    2.75
    b
    2.72
    f
    2.69
     Makes
    2.69
     Its
    2.66
    る
    2.63
    Activations Density 0.026%

    No Known Activations