© 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. 34-GEMMASCOPE-RES-131K
    7. 12232
    Prev
    Next
    INDEX
    Explanations

    indicating numerical multiples

    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
    これも
    -0.85
    BeforeEach
    -0.79
    ить
    -0.79
     mohl
    -0.78
    bbling
    -0.71
     изба
    -0.71
     richesse
    -0.71
    toolkit
    -0.71
    TokenType
    -0.71
     Auftritt
    -0.70
    POSITIVE LOGITS
     times
    5.41
    times
    3.20
     twice
    3.17
     Times
    3.08
    Times
    3.02
     veces
    3.02
    twice
    3.00
     TIMES
    2.91
    Twice
    2.72
    TIMES
    2.72
    Activations Density 0.059%

    No Known Activations