© 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. 71441
    Prev
    Next
    INDEX
    Explanations

    Spectrally filtering, risk, hospital, standing, food

    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
    ↵
    0.52
    _
    0.49
    +
    0.48
     +
    0.47
    -
    0.46
    )
    0.46
    ;
    0.46
    /
    0.45
    ↵↵
    0.45
    .
    0.45
    POSITIVE LOGITS
    avacanam
    0.34
     insanların
    0.34
     människor
    0.33
    Gosudarstvennyj
    0.32
    acariy
    0.32
     discíp
    0.32
    痱
    0.32
    atthakath
    0.31
    gdock
    0.31
     bactéries
    0.31
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.