© 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. 221696
    Prev
    Next
    INDEX
    Explanations

    lists, parentheses, and commas

    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
     Num
    0.39
    NUM
    0.39
     #+#
    0.38
    BIUM
    0.38
    문을
    0.38
    역
    0.36
     논
    0.36
     num
    0.36
     역
    0.36
    ត្ត
    0.35
    POSITIVE LOGITS
     messaging
    0.42
    mike
    0.40
    anki
    0.40
     હિ
    0.40
    Caribbean
    0.39
     sentencing
    0.39
     কেজি
    0.39
     लाभदायक
    0.38
    വൻ
    0.37
    ambe
    0.37
    Activations Density 0.000%

    No Known Activations