© 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. 31-GEMMASCOPE-2-RES-262K
    7. 90258
    Prev
    Next
    INDEX
    Explanations

    how and where

    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_31_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
     Listening
    0.49
    謖
    0.47
    一直
    0.44
    の大
    0.44
     listened
    0.44
    アカ
    0.44
     கேட்ட
    0.43
     Greenland
    0.43
     Active
    0.42
     till
    0.42
    POSITIVE LOGITS
    Pac
    0.46
    iams
    0.46
    MAGNET
    0.45
    studded
    0.43
    ​
    0.43
    strictly
    0.42
    ruci
    0.41
    CLUSTER
    0.41
    mirror
    0.40
    no
    0.40
    Activations Density 0.002%

    No Known Activations