© 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. 6437
    Prev
    Next
    INDEX
    Explanations

    negative statements and finances

    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
     หน
    0.49
    abbanti
    0.48
     TokenType
    0.47
    angled
    0.46
    峮
    0.46
     DENUMIRE
    0.46
     国家
    0.46
    anglement
    0.45
     moeilijk
    0.45
    ன்னி
    0.45
    POSITIVE LOGITS
    ل
    0.50
    ك
    0.49
     ke
    0.46
    v
    0.45
     with
    0.44
    Nicole
    0.43
    Google
    0.42
    with
    0.42
    e
    0.41
    ATTR
    0.41
    Activations Density 0.000%

    No Known Activations