© 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. 34-GEMMASCOPE-RES-131K
    7. 107763
    Prev
    Next
    INDEX
    Explanations

    attraction

    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
    xfb
    -0.92
    YSQL
    -0.84
    GONE
    -0.81
    álogo
    -0.79
     LaTeX
    -0.77
     död
    -0.77
    störungen
    -0.75
     Bb
    -0.74
     vot
    -0.74
    ursday
    -0.74
    POSITIVE LOGITS
     Related
    0.84
     experiencing
    0.82
     related
    0.81
     Gnade
    0.81
     limited
    0.77
     reiterated
    0.73
    related
    0.72
     here
    0.71
     miệng
    0.71
     Unlimited
    0.69
    Activations Density 0.051%

    No Known Activations