© 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. 13524
    Prev
    Next
    INDEX
    Explanations

    apologize for inconvenience this

    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
     Saleem
    0.53
    '_
    0.42
     র
    0.40
    GIL
    0.40
     prizes
    0.40
    od
    0.40
    "
    0.40
    ই
    0.40
     definiciones
    0.39
     exports
    0.39
    POSITIVE LOGITS
    рно
    0.53
    ीट
    0.52
     Bonifacio
    0.47
    力和
    0.45
     kebanyakan
    0.44
    alista
    0.42
     knelt
    0.42
     byt
    0.42
    anego
    0.42
    캄
    0.42
    Activations Density 0.002%

    No Known Activations