© 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. 17773
    Prev
    Next
    INDEX
    Explanations

    सीखना पसंद

    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
    ponym
    0.48
     이는
    0.47
     모든
    0.44
     তরফে
    0.44
     설
    0.43
     protrusions
    0.42
     saha
    0.41
     경우
    0.41
     sentimental
    0.41
     seductive
    0.41
    POSITIVE LOGITS
     и
    0.65
     మాత్రమే
    0.56
    ப்படுத்த
    0.55
     और
    0.54
    и
    0.54
    ON
    0.53
     करने
    0.52
    નું
    0.52
    を
    0.52
     এবং
    0.52
    Activations Density 0.004%

    No Known Activations