© 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. 67895
    Prev
    Next
    INDEX
    Explanations

    operating procedures and specific items

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

    Russian, Arabic, Korean, Europe, security

    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
    αν
    0.56
    λα
    0.51
    εν
    0.47
    ii
    0.47
    β
    0.46
    제곱
    0.45
    Α
    0.45
    ολ
    0.44
     Συν
    0.44
    ΗΣ
    0.44
    POSITIVE LOGITS
     보안
    0.58
     morality
    0.52
     veil
    0.52
    𝙣
    0.52
     зоне
    0.51
     أوروبا
    0.50
     motivations
    0.49
     зону
    0.49
     середине
    0.49
     داخلی
    0.48
    Activations Density 0.000%

    No Known Activations