© 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. 192575
    Prev
    Next
    INDEX
    Explanations

    needs investment or cost

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

    meaning, purpose, values

    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
     ανάπτυ
    0.53
     habitation
    0.51
     судеб
    0.51
    鄢
    0.50
    BURN
    0.49
     burn
    0.47
     сіль
    0.45
     ентите
    0.45
    狨
    0.44
    称为
    0.44
    POSITIVE LOGITS
    shoz
    0.52
    nof
    0.50
    ்க
    0.50
    rms
    0.49
    zak
    0.49
    }}}}$
    0.49
    ulta
    0.47
    sw
    0.47
    ritos
    0.46
    les
    0.45
    Activations Density 0.001%

    No Known Activations