© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 12483
    Prev
    Next
    INDEX
    Explanations

    self- in compounds

    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_53_width_262k_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
     adob
    0.36
    ক্টো
    0.35
    वाड़ा
    0.34
    ጋ
    0.33
     jdbcTemplate
    0.33
     ረ
    0.33
    니아
    0.33
    وشن
    0.32
    ಭಾಗ
    0.31
    cherichia
    0.31
    POSITIVE LOGITS
     self
    4.63
     Self
    4.38
    Self
    4.19
     SELF
    3.78
    self
    3.77
     само
    3.41
     सेल्फ
    3.30
    自
    3.27
     Selbst
    3.25
    SELF
    3.20
    Activations Density 0.217%

    No Known Activations