© 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. 99275
    Prev
    Next
    INDEX
    Explanations

    new and unused condition

    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
    unit
    -0.78
     nons
    -0.71
    payload
    -0.69
    进步
    -0.66
     Know
    -0.66
    Bety
    -0.66
     כמה
    -0.66
     bullied
    -0.66
     Wandel
    -0.65
     coded
    -0.65
    POSITIVE LOGITS
     Unused
    0.96
     unused
    0.84
     condition
    0.78
    ıç
    0.76
    Condition
    0.74
     Condition
    0.73
     verborgen
    0.73
     lengte
    0.71
    周泽
    0.71
    ณี
    0.71
    Activations Density 0.050%

    No Known Activations