© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 71653
    Prev
    Next
    INDEX
    Explanations

    spirit of cricket

    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_22/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
    𖡼
    -2.13
     for
    -2.05
     if
    -2.03
    牁
    -2.03
    硯
    -1.93
    🦋
    -1.91
    ~♪
    -1.87
     fotball
    -1.86
     revital
    -1.81
    〜!
    -1.80
    POSITIVE LOGITS
    ’
    2.50
     
    2.39
     VERY
    2.19
     exceedingly
    2.19
     extremely
    2.16
     unbelievably
    2.13
     gigantic
    2.11
    '
    2.05
     astounding
    2.03
     astonishing
    2.02
    Activations Density 0.000%

    No Known Activations