© 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. 40-GEMMASCOPE-2-RES-262K
    7. 191624
    Prev
    Next
    INDEX
    Explanations

    code, text, or language structure

    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_40_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
    googleapis
    0.42
    Eastern
    0.42
    fs
    0.38
    Fs
    0.38
    Parse
    0.38
    獭
    0.38
     flaves
    0.38
    front
    0.38
    Ya
    0.37
    fstream
    0.37
    POSITIVE LOGITS
    榱
    0.43
    ስቃ
    0.43
     vandalism
    0.42
    ेंडर
    0.39
    至於
    0.38
     எதிர்பார
    0.38
    рито
    0.38
     curriculum
    0.38
     скоро
    0.38
    क्या
    0.37
    Activations Density 0.000%

    No Known Activations