© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 144493
    Prev
    Next
    INDEX
    Explanations

    teacher was, pdf /sellers under

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

    explicit content and warnings

    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
    Negative Logits
     recipe
    0.46
     pulsar
    0.45
     ઘ
    0.44
     militants
    0.43
     نوم
    0.43
     cure
    0.43
     सर्
    0.42
     වඩා
    0.42
    )[
    0.42
     sinner
    0.41
    POSITIVE LOGITS
    timestamps
    0.49
    risk
    0.48
    ridge
    0.47
    an
    0.46
    ley
    0.46
    OI
    0.45
    hasOwnProperty
    0.44
    avn
    0.44
    v
    0.44
    ales
    0.44
    Activations Density 0.001%

    No Known Activations