© 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. 44523
    Prev
    Next
    INDEX
    Explanations

    non-english words/roots

    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
     आतंकवादी
    0.48
     সর্বোচ্চ
    0.47
     दहशत
    0.46
     เพื่อ
    0.44
     상황
    0.44
     非
    0.42
     항목
    0.42
    感謝
    0.42
     целях
    0.41
     терро
    0.41
    POSITIVE LOGITS
    suff
    0.46
     gehörte
    0.46
    ylle
    0.44
     autrefois
    0.44
    phil
    0.42
     oedd
    0.42
    ἴ
    0.42
    aqua
    0.41
    ékek
    0.41
     agrad
    0.41
    Activations Density 0.017%

    No Known Activations