© 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. 190232
    Prev
    Next
    INDEX
    Explanations

    periods and commas

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

    then, strategies, or Uzbekistan

    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
     acompañado
    0.55
     hafif
    0.47
     （
    0.47
     någon
    0.46
     och
    0.46
     Buf
    0.46
     amel
    0.45
     et
    0.45
     vä
    0.45
     Tok
    0.45
    POSITIVE LOGITS
    ALY
    0.46
    these
    0.46
    ೮
    0.44
    These
    0.43
    hyper
    0.43
    countable
    0.43
    arrows
    0.43
    טר
    0.43
    noy
    0.42
    不管是
    0.42
    Activations Density 0.000%

    No Known Activations