© 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. 85665
    Prev
    Next
    INDEX
    Explanations

    HTML spaces and references

    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
    舠
    -1.79
    觏
    -1.69
    
    -1.63
     squishy
    -1.54
    +");
    -1.52
     vorige
    -1.49
     quelque
    -1.48
     obviamente
    -1.47
    hemd
    -1.46
     According
    -1.45
    POSITIVE LOGITS
     of
    2.09
    ↵
    1.92
    },
    1.90
     腳
    1.67
     similar
    1.66
    and
    1.65
    汌
    1.63
    from
    1.59
    WHAT
    1.59
    盌
    1.59
    Activations Density 0.028%

    No Known Activations