© 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. 226910
    Prev
    Next
    INDEX
    Explanations

    before choosing, regeneration browsed

    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
     приви
    0.50
     Sunglasses
    0.44
    လေး
    0.42
    美国的
    0.42
     presc
    0.41
     delitos
    0.40
     дальнейшем
    0.40
     convicts
    0.40
     mesure
    0.40
     လ
    0.40
    POSITIVE LOGITS
    urat
    0.50
    bett
    0.49
    atual
    0.48
    égal
    0.46
    ATION
    0.46
    演出
    0.45
     surging
    0.45
     沒有
    0.45
    licking
    0.43
     betting
    0.42
    Activations Density 0.004%

    No Known Activations