© 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-65K
    7. 55436
    Prev
    Next
    INDEX
    Explanations

    lists 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_65k_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
    0.45
     reward
    0.44
     বলেন
    0.44
     о
    0.42
     이름을
    0.42
     name
    0.42
     newspapers
    0.42
     replace
    0.41
     slug
    0.40
     publications
    0.40
    POSITIVE LOGITS
    Бі
    0.45
    瘢
    0.45
    ھیں
    0.44
    Вели
    0.44
    篾
    0.44
    崆
    0.44
    ಿಕೊಂಡ
    0.43
    中医
    0.43
    团结
    0.42
    opposition
    0.42
    Activations Density 0.002%

    No Known Activations