© 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. 10-GEMMASCOPE-RES-131K
    7. 112555
    Prev
    Next
    INDEX
    Explanations

    like me

    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
    t
    -1.78
     the
    -1.76
    
    -1.61
    嘮
    -1.57
     aggiungere
    -1.47
    喜歡的
    -1.43
    に関して
    -1.43
    m
    -1.42
     bedeut
    -1.41
    翆
    -1.40
    POSITIVE LOGITS
    geſ
    1.88
    )
    1.84
    <h2>
    1.78
    又能
    1.77
    也能
    1.71
    8
    1.70
    และ
    1.67
     decorativa
    1.59
    ERICAN
    1.57
     маленьких
    1.53
    Activations Density 0.008%

    No Known Activations