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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76893
    Prev
    Next
    INDEX
    Explanations

    avoid not

    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
     আগের
    0.47
     এটির
    0.46
     আগে
    0.43
    ಾಗಿದೆ
    0.43
    おすすめです
    0.43
     Infine
    0.43
    ઢી
    0.42
    <unused85>
    0.42
    Excellent
    0.42
    গত
    0.42
    POSITIVE LOGITS
     cruise
    0.46
    г
    0.46
     cruises
    0.46
     tape
    0.45
     speculation
    0.45
     stool
    0.45
     spectrosc
    0.43
     തിര
    0.42
     رجل
    0.42
    вер
    0.42
    Activations Density 0.006%

    No Known Activations