© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 453
    Prev
    Next
    INDEX
    Explanations

    precedes phrases

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

    how can

    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_262k_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
    /
    0.53
    of
    0.50
    均衡
    0.45
     overwhelmingly
    0.44
    represented
    0.43
    ij
    0.42
    த்திர
    0.41
    overflow
    0.41
    each
    0.41
    .
    0.41
    POSITIVE LOGITS
     نیاز
    0.59
     структуры
    0.57
     نقطه
    0.54
     فری
    0.54
     لینک
    0.54
     કેટલાક
    0.54
     പക
    0.53
     રાજ્ય
    0.52
     propriété
    0.51
    leicht
    0.51
    Activations Density 0.001%

    No Known Activations