© 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. 76866
    Prev
    Next
    INDEX
    Explanations

    in there or in the

    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
    Its
    -1.05
     从
    -0.98
    这种
    -0.96
    を持つ
    -0.94
    iramente
    -0.93
    void
    -0.93
    This
    -0.93
     कई
    -0.90
    他人
    -0.90
    各种
    -0.90
    POSITIVE LOGITS
     there
    6.03
     here
    3.63
     там
    2.84
     هناك
    2.47
     ahí
    2.42
    there
    2.41
    There
    2.31
     allí
    2.30
     آنجا
    2.02
     acolo
    1.95
    Activations Density 0.080%

    No Known Activations