© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19789
    Prev
    Next
    INDEX
    Explanations

    otherwise specified or mentioned

    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
    阿里
    0.42
    篂
    0.41
    羮
    0.40
     Whats
    0.40
     Sare
    0.39
     registro
    0.38
    க்கி
    0.37
     Nomination
    0.37
     Tengo
    0.37
     éventuellement
    0.37
    POSITIVE LOGITS
    あなたは
    0.42
    或
    0.42
     prefers
    0.40
    你可以
    0.40
    Bạn
    0.40
    每个人
    0.39
     অনুষ্ঠ
    0.39
    remain
    0.39
     reverts
    0.38
    nehm
    0.38
    Activations Density 0.002%

    No Known Activations