© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 111675
    Prev
    Next
    INDEX
    Explanations

    valid search

    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
    !
    0.43
     impacto
    0.42
     Interaction
    0.40
     ellas
    0.40
     Than
    0.40
     and
    0.39
     Así
    0.39
     Applying
    0.39
     así
    0.38
     Schools
    0.38
    POSITIVE LOGITS
    ダウンロード
    0.54
    լ
    0.47
     메모
    0.46
     جشنواره
    0.45
    ਘ
    0.45
     २०१
    0.45
    ॉफ्ट
    0.45
     incriminating
    0.44
     spreadsheets
    0.44
     ২০১৪
    0.44
    Activations Density 0.007%

    No Known Activations