© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10226
    Prev
    Next
    INDEX
    Explanations

    separator characters

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

    separators like --- and ____

    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_40_width_16k_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
    鈔
    0.47
    酞
    0.46
    .#
    0.43
    湪
    0.42
     /**
    0.40
     :-
    0.40
    ørte
    0.40
    ál
    0.40
    栯
    0.39
    uchs
    0.39
    POSITIVE LOGITS
    t
    0.53
    total
    0.46
    detection
    0.46
    ванням
    0.45
    test
    0.44
    にした
    0.44
    둔
    0.44
    тів
    0.42
    together
    0.42
    ො
    0.41
    Activations Density 0.020%

    No Known Activations