© 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. 51080
    Prev
    Next
    INDEX
    Explanations

    quantity and description

    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
     ή
    0.46
     অথবা
    0.45
     hoặc
    0.44
    ình
    0.40
     އ
    0.39
     Anand
    0.39
    或
    0.38
     ወይም
    0.37
     ଏ
    0.37
     or
    0.37
    POSITIVE LOGITS
    lista
    0.50
     setiap
    0.48
     cantidad
    0.46
     rassembl
    0.46
     abstra
    0.46
    numero
    0.45
     Consistency
    0.45
    dokument
    0.45
     relevancia
    0.45
     बढ़ावा
    0.45
    Activations Density 0.007%

    No Known Activations