© 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. 53192
    Prev
    Next
    INDEX
    Explanations

    tell or not tell

    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
     pump
    0.55
    I
    0.47
     squirrel
    0.45
    pump
    0.44
     pumps
    0.43
    PEL
    0.43
    Q
    0.42
     tournaments
    0.42
     multil
    0.42
    BMI
    0.42
    POSITIVE LOGITS
     Dostupné
    0.48
    itte
    0.46
    ✧
    0.43
     bodo
    0.43
     desee
    0.42
     sigurn
    0.42
     Pago
    0.41
     प्राणी
    0.41
    يلي
    0.41
    ̵
    0.41
    Activations Density 0.002%

    No Known Activations