© 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. 30236
    Prev
    Next
    INDEX
    Explanations

    numbers, symbols, and specific terms

    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
     ecologists
    0.49
     liberties
    0.48
    PREFIX
    0.48
    ១
    0.47
     لكل
    0.47
     priors
    0.46
     epidemiological
    0.46
    udarstvennyj
    0.45
    uffix
    0.45
    ៨
    0.45
    POSITIVE LOGITS
     Wagner
    0.46
     will
    0.46
     daha
    0.44
    发电
    0.44
    רה
    0.44
     Monte
    0.44
     Villa
    0.43
     Menon
    0.43
     Gro
    0.43
     had
    0.42
    Activations Density 0.000%

    No Known Activations