© 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. 114125
    Prev
    Next
    INDEX
    Explanations

    states or transitions

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

    estimating figures, analyses, and diversity

    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
     sd
    0.46
    IW
    0.44
    ৰি
    0.44
    <0xF3>
    0.44
     overwrite
    0.44
    <0xA6>
    0.43
    Kansas
    0.43
    Canc
    0.43
     divulg
    0.42
    Curt
    0.42
    POSITIVE LOGITS
     ":
    0.47
    ontinuous
    0.45
     переход
    0.44
     is
    0.42
    vertine
    0.41
     Tuck
    0.41
    osters
    0.40
     Modes
    0.40
     transitioned
    0.40
    közi
    0.40
    Activations Density 0.001%

    No Known Activations