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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69069
    Prev
    Next
    INDEX
    Explanations

    duration up to now

    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
     of
    -2.22
     for
    -1.72
     the
    -1.67
     from
    -1.66
     الرغم
    -1.53
    decoração
    -1.45
    }$.
    -1.42
    如同
    -1.41
     попробу
    -1.40
     但
    -1.38
    POSITIVE LOGITS
     now
    1.90
     работал
    1.59
     this
    1.56
     próximos
    1.42
     necesitaba
    1.38
    されていて
    1.33
     seguras
    1.33
     hà
    1.32
     hechas
    1.32
    谂
    1.31
    Activations Density 0.025%

    No Known Activations