© 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. 10-GEMMASCOPE-RES-131K
    7. 86892
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

    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_10/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
     
    -2.84
    تیجه
    -2.73
    CHREIB
    -2.59
    </em>
    -2.58
    It
    -2.56
    T
    -2.53
    哪怕
    -2.48
    на
    -2.45
    都是
    -2.42
     .
    -2.41
    POSITIVE LOGITS
    tacte
    2.81
    튿
    2.69
    玙
    2.69
    y
    2.44
    ophageal
    2.44
    LYPH
    2.42
    嶮
    2.42
    KELEY
    2.41
    ichtete
    2.38
    快点
    2.38
    Activations Density 0.173%

    No Known Activations