© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 109003
    Prev
    Next
    INDEX
    Explanations

    adverbial modifiers and descriptions

    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
     incentivize
    0.54
     retouch
    0.51
     loopholes
    0.48
    🦌
    0.47
     reintegr
    0.47
    ጠቀም
    0.45
     criticize
    0.43
    чиго
    0.43
    icollis
    0.43
     recapture
    0.43
    POSITIVE LOGITS
    則是
    0.48
    ROLE
    0.47
     Mille
    0.42
    disp
    0.41
    空间
    0.41
    内的
    0.41
    表的
    0.41
    尚
    0.41
    tabla
    0.40
     நீ
    0.40
    Activations Density 0.005%

    No Known Activations