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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 12422
    Prev
    Next
    INDEX
    Explanations

    choices and options

    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_40_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
     fuselage
    0.47
     callous
    0.47
    รถ
    0.43
     bolas
    0.43
     be
    0.42
     пом
    0.41
     童
    0.41
    WE
    0.40
     jagged
    0.40
    boli
    0.39
    POSITIVE LOGITS
     available
    0.55
     Available
    0.55
     Options
    0.55
     Option
    0.54
     option
    0.54
    ти
    0.52
     opções
    0.52
     disponíveis
    0.50
     options
    0.49
     earthqu
    0.49
    Activations Density 0.016%

    No Known Activations