© 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. 16-GEMMASCOPE-2-RES-262K
    7. 6294
    Prev
    Next
    INDEX
    Explanations

    words after punctuation

    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_16_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
    ری
    0.44
    א
    0.31
    하지만
    0.30
    이
    0.30
    ח
    0.29
    ">)</
    0.29
     которые
    0.28
     kola
    0.28
     overtake
    0.28
    তাসীন
    0.28
    POSITIVE LOGITS
    .
    0.44
    0.41
     (
    0.34
    H
    0.34
    </b>
    0.33
    ý
    0.33
       
    0.32
    ↵↵
    0.31
    ým
    0.30
    could
    0.30
    Activations Density 1.571%

    No Known Activations