© 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. 76835
    Prev
    Next
    INDEX
    Explanations

    emotion or state of being

    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
    Serial
    0.52
    mark
    0.48
    mill
    0.45
     আদাল
    0.45
    ט
    0.44
    und
    0.44
    uster
    0.43
    tax
    0.43
    ("|"+"
    0.43
    alura
    0.43
    POSITIVE LOGITS
     facilité
    0.47
     morrer
    0.47
     stirrer
    0.46
    зы
    0.46
    Ꮫ
    0.44
    ায়ে
    0.43
     saúde
    0.42
     Stéphane
    0.42
     términos
    0.42
     lymphatic
    0.42
    Activations Density 0.003%

    No Known Activations