© 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. 40-GEMMASCOPE-2-RES-262K
    7. 35560
    Prev
    Next
    INDEX
    Explanations

    late 2023 / early 2024

    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_40_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
    ②
    0.45
    WOR
    0.43
     AFTER
    0.43
    [_
    0.41
     HAR
    0.40
    ③
    0.40
     OTHER
    0.40
    其余
    0.39
     অথবা
    0.39
    ⑤
    0.39
    POSITIVE LOGITS
     early
    1.08
    early
    0.95
     frühen
    0.80
    早
    0.72
    Early
    0.70
     Early
    0.68
     into
    0.66
     начале
    0.62
     awal
    0.61
    早期
    0.59
    Activations Density 0.022%

    No Known Activations