© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 13673
    Prev
    Next
    INDEX
    Explanations

    cause physical

    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_65k_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
     Poincaré
    0.45
    ’
    0.44
     غير
    0.44
     attenu
    0.44
     imper
    0.43
     indépend
    0.43
     evoc
    0.43
     implic
    0.42
     lung
    0.42
     impul
    0.42
    POSITIVE LOGITS
    uanya
    0.47
    ovne
    0.46
    ovno
    0.45
    ('&
    0.45
    тала
    0.44
    airro
    0.44
    gpio
    0.43
    ငံ
    0.43
    aments
    0.43
    inning
    0.43
    Activations Density 0.014%

    No Known Activations