© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13734
    Prev
    Next
    INDEX
    Explanations

    words starting with a

    np_acts-logits-general · gemini-2.5-flash-lite

    aluminum or asset recovery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    كان
    0.76
    €™
    0.75
     botas
    0.72
    د
    0.72
    д
    0.68
    <unused2231>
    0.68
     canciones
    0.66
    的名字
    0.65
    arote
    0.65
     dificuldade
    0.64
    POSITIVE LOGITS
    2
    0.86
     thaliana
    0.78
    ă
    0.70
    ę
    0.70
    ことを
    0.66
    INA
    0.64
    ET
    0.63
    AF
    0.63
    ON
    0.63
    ric
    0.63
    Activations Density 2.609%

    No Known Activations