© 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. 7576
    Prev
    Next
    INDEX
    Explanations

    lost things

    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
    적이
    0.43
    olf
    0.42
    uminous
    0.41
    uez
    0.41
    с
    0.41
     দেবী
    0.40
     combustible
    0.40
    жи
    0.39
    こともある
    0.39
    腔
    0.38
    POSITIVE LOGITS
     povos
    0.54
     opio
    0.50
     فبراير
    0.50
     milhares
    0.49
     estoppel
    0.48
    사람
    0.47
     vooraf
    0.47
     padres
    0.47
     ಕಾರ್
    0.47
     inundated
    0.47
    Activations Density 0.000%

    No Known Activations