© 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. 141419
    Prev
    Next
    INDEX
    Explanations

    legal, financial, or personal status updates

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

    qualifiers and disclaimers

    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
    사람
    0.47
    这时候
    0.44
    Journey
    0.42
    ήμερα
    0.42
    Quartz
    0.42
    People
    0.41
    Register
    0.41
     사람은
    0.41
    ↵
    0.41
    coordinator
    0.41
    POSITIVE LOGITS
    ricult
    0.45
     ಮಿಶ್ರ
    0.44
     vitth
    0.44
    㽛
    0.41
    asidd
    0.41
     ಗುಣ
    0.40
    觡
    0.40
     fornis
    0.39
    ੇ
    0.39
    厙
    0.39
    Activations Density 0.001%

    No Known Activations