© 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. 71802
    Prev
    Next
    INDEX
    Explanations

    programming language keywords

    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
     akong
    -0.95
     Krzysz
    -0.93
     Songtext
    -0.88
    稍微
    -0.88
    '
    -0.87
    Ħ
    -0.87
     utilisés
    -0.85
    >−
    -0.84
     стоимо
    -0.84
     Phila
    -0.83
    POSITIVE LOGITS
    ſi
    1.16
    嚆
    1.09
    ೪
    1.04
     rêver
    1.01
    ೬
    1.00
    Manufact
    0.99
     équ
    0.98
    enciais
    0.97
     stad
    0.97
     your
    0.97
    Activations Density 0.032%

    No Known Activations