© 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. 79970
    Prev
    Next
    INDEX
    Explanations

    he she and subsequent verbs

    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
     gives
    0.47
     intending
    0.47
     intends
    0.45
    ’
    0.44
     makes
    0.41
     retains
    0.40
    केर
    0.40
     eliminates
    0.40
     avoids
    0.40
     keeps
    0.39
    POSITIVE LOGITS
     sendiri
    0.42
    現在
    0.41
     dibawa
    0.39
     practised
    0.38
    撈
    0.38
    就知道
    0.38
    alth
    0.38
    тету
    0.37
    娠
    0.37
    ян
    0.36
    Activations Density 0.002%

    No Known Activations