© 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. 39996
    Prev
    Next
    INDEX
    Explanations

    list items or examples

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

    Detects tokens that mark an abbreviated list ending (i.e., the "etc."-type list-closure token).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    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
     abges
    0.35
     ски
    0.35
    pati
    0.35
    >>&
    0.35
    biggr
    0.34
    squre
    0.34
     зап
    0.34
    跛
    0.34
    Runner
    0.33
    скі
    0.33
    POSITIVE LOGITS
     bag
    0.43
    AZ
    0.40
    bag
    0.39
     Coy
    0.38
     Lucy
    0.38
     Bag
    0.38
     WE
    0.37
    ACY
    0.37
     Cow
    0.37
     AZ
    0.37
    Activations Density 0.008%

    No Known Activations