© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 61326
    Prev
    Next
    INDEX
    Explanations

    preference for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initiating
    0.38
    лум
    0.37
     prism
    0.37
     member
    0.35
    thunder
    0.35
    owners
    0.34
     interprets
    0.34
    ຳ
    0.34
    ູນ
    0.34
    unov
    0.34
    POSITIVE LOGITS
     здесь
    0.44
    考試
    0.43
    撓
    0.42
    :\
    0.42
    敵人
    0.42
     Matemat
    0.42
     condição
    0.41
     bahasa
    0.41
     Matemática
    0.41
     Comerc
    0.41
    Activations Density 0.002%

    No Known Activations