© 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. 109929
    Prev
    Next
    INDEX
    Explanations

    options and variations

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

    describing things with adjectives

    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
    이
    0.49
     STORE
    0.48
     IN
    0.47
     raff
    0.46
     operator
    0.45
     Cynthia
    0.44
    가
    0.44
     mascot
    0.43
    序列
    0.43
    我要
    0.42
    POSITIVE LOGITS
    𝗆
    0.53
    nons
    0.45
    ieso
    0.45
     dû
    0.45
     callous
    0.42
     सूरत
    0.41
    ेश्च
    0.41
     nons
    0.41
    ਿਰ
    0.40
    ेड
    0.39
    Activations Density 0.000%

    No Known Activations