© 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. 92156
    Prev
    Next
    INDEX
    Explanations

    legal or financial decisions

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

    qualities and situations

    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
    зит
    0.47
     dicion
    0.46
     independencia
    0.44
     indépend
    0.44
    istencia
    0.44
    茨
    0.44
     الگ
    0.43
    对话
    0.42
    EnumType
    0.42
    λούν
    0.42
    POSITIVE LOGITS
     ...,
    0.48
     +(
    0.45
     `>=`,
    0.44
     MDS
    0.44
     STS
    0.44
     Lyric
    0.43
    ực
    0.42
     Benson
    0.42
     '',
    0.42
    ารย์
    0.42
    Activations Density 0.000%

    No Known Activations