© 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. 40-GEMMASCOPE-2-RES-262K
    7. 120203
    Prev
    Next
    INDEX
    Explanations

    privacy and cheerful

    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
     owing
    0.42
     Tay
    0.40
     grit
    0.39
     cords
    0.38
     prostředí
    0.38
    мила
    0.38
    痍
    0.38
     stripping
    0.37
     ciertos
    0.37
     miRNAs
    0.37
    POSITIVE LOGITS
     cava
    0.43
     burst
    0.40
    Obama
    0.40
    fad
    0.39
     pega
    0.39
    パ
    0.39
    Radi
    0.38
     उद
    0.38
     freestyle
    0.38
    toothpaste
    0.38
    Activations Density 0.001%

    No Known Activations