© 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. 22-GEMMASCOPE-RES-131K
    7. 12437
    Prev
    Next
    INDEX
    Explanations

    code punctuation and keywords

    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
    ָּ
    -0.94
    ﾚ
    -0.86
     their
    -0.83
     our
    -0.82
    tess
    -0.79
    Moj
    -0.79
     Njema
    -0.79
    impan
    -0.78
    impossible
    -0.77
    blond
    -0.77
    POSITIVE LOGITS
    𝙖
    0.86
     boston
    0.80
     😅
    0.80
     Pesticide
    0.79
     satunya
    0.79
    ğini
    0.78
    ENTY
    0.77
    ʄ
    0.77
     Segu
    0.77
     tæ
    0.77
    Activations Density 0.000%

    No Known Activations