© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67815
    Prev
    Next
    INDEX
    Explanations

    german pronoun ich

    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
    on
    -3.92
    an
    -3.23
     “
    -2.73
    <em>
    -2.73
    i
    -2.72
    ان
    -2.66
    ا
    -2.63
    of
    -2.56
    ↵
    -2.44
     Their
    -2.36
    POSITIVE LOGITS
    s
    3.97
    俛
    3.14
    朏
    2.98
    derdag
    2.91
    pecabe
    2.83
    StoryboardSegue
    2.81
    
    2.64
    ich
    2.59
    𐄙
    2.50
    ቍ
    2.47
    Activations Density 0.006%

    No Known Activations