© 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. 10-GEMMASCOPE-RES-131K
    7. 129814
    Prev
    Next
    INDEX
    Explanations

    editing

    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
     with
    -1.98
     for
    -1.88
    ing
    -1.73
    but
    -1.63
     They
    -1.63
     Unfortunately
    -1.61
     But
    -1.59
     інших
    -1.56
     Technically
    -1.53
     Notably
    -1.53
    POSITIVE LOGITS
    ↵
    1.86
    </b>
    1.82
    }$.
    1.77
    </sup>
    1.68
     Saltar
    1.66
    eſt
    1.65
    bę
    1.55
     İ
    1.52
    ј
    1.52
     gustado
    1.49
    Activations Density 0.016%

    No Known Activations