© 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. 71493
    Prev
    Next
    INDEX
    Explanations

    temperature, digit, members

    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
     disappear
    0.54
     immune
    0.51
     vanish
    0.50
     disability
    0.49
     disappearance
    0.46
     vanishes
    0.45
     vanishing
    0.45
     <
    0.45
     password
    0.44
     scars
    0.44
    POSITIVE LOGITS
    炜
    0.48
    igned
    0.45
    ERAL
    0.45
    هداف
    0.45
    ढ़
    0.43
    ária
    0.43
    eem
    0.43
    졔
    0.43
    晤
    0.42
    спользова
    0.42
    Activations Density 0.003%

    No Known Activations