© 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. 22017
    Prev
    Next
    INDEX
    Explanations

    made his way

    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
    7
    -1.85
     или
    -1.80
    8
    -1.73
     hacerte
    -1.67
    6
    -1.63
    9
    -1.60
     where
    -1.59
     pytania
    -1.56
     like
    -1.56
    或
    -1.55
    POSITIVE LOGITS
    𝑥
    1.72
     beide
    1.70
    1.67
    щита
    1.62
     participa
    1.61
    おもしろ
    1.58
     

    1.55
     itemprop
    1.54
    >}
    1.52
     refugi
    1.52
    Activations Density 0.036%

    No Known Activations