© 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. 216021
    Prev
    Next
    INDEX
    Explanations

    scientific names and references

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

    discovery, description, classification

    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
    量は
    0.44
    /$
    0.43
     Tạo
    0.43
    /−
    0.42
     |
    0.42
    enteric
    0.42
    :$
    0.41
    primary
    0.41
    りと
    0.40
    、$
    0.40
    POSITIVE LOGITS
     леген
    0.43
     широ
    0.40
     veck
    0.38
     posthum
    0.37
     shocked
    0.37
     выска
    0.37
    ॅ
    0.36
    шча
    0.36
    넋
    0.36
     casually
    0.36
    Activations Density 0.004%

    No Known Activations