© 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. 34-GEMMASCOPE-RES-131K
    7. 49662
    Prev
    Next
    INDEX
    Explanations

    technical code and documentation

    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_34/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
    ներ
    -0.79
     Watkins
    -0.79
     Forman
    -0.75
     Milford
    -0.74
    κη
    -0.71
    umacher
    -0.70
    ॉक
    -0.70
     stage
    -0.69
     public
    -0.68
     Larry
    -0.68
    POSITIVE LOGITS
    Shoulder
    0.84
    併
    0.80
     Dina
    0.78
     deixando
    0.77
     Pointer
    0.76
    spotify
    0.76
    ]}{
    0.75
    ׇ
    0.74
     Correo
    0.74
     NTIS
    0.74
    Activations Density 0.002%

    No Known Activations