© 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. 103672
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers and types

    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
    laka
    -0.82
    MatButtonModule
    -0.77
     thinks
    -0.76
     comes
    -0.76
    に行った
    -0.72
     this
    -0.71
     wears
    -0.71
     Ceremonies
    -0.70
     suggests
    -0.70
    父子
    -0.70
    POSITIVE LOGITS
    LL
    1.08
     long
    1.01
    unsigned
    0.95
    uint
    0.94
    long
    0.93
     uint
    0.88
     unsigned
    0.88
    ziell
    0.84
     integer
    0.84
     изме
    0.84
    Activations Density 0.089%

    No Known Activations