© 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. 200426
    Prev
    Next
    INDEX
    Explanations

    Project Hail Mary, The Martian

    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
     вр
    0.52
    できません
    0.47
     Вул
    0.45
     estrem
    0.45
    炇
    0.44
     sar
    0.44
     poes
    0.44
     extrapolated
    0.43
     kammam
    0.43
     пов
    0.42
    POSITIVE LOGITS
    Kit
    0.46
    och
    0.43
    kilomet
    0.43
    My
    0.43
    Label
    0.42
    Gob
    0.41
    min
    0.40
    K
    0.40
    ty
    0.40
    hab
    0.39
    Activations Density 0.002%

    No Known Activations