© 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. 40648
    Prev
    Next
    INDEX
    Explanations

    chess player

    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
     usuarios
    0.49
     praises
    0.45
     CASA
    0.44
     学生
    0.42
     territorios
    0.42
    㬶
    0.42
     CIM
    0.41
    atsii
    0.41
    不会
    0.41
    wości
    0.41
    POSITIVE LOGITS
    х
    0.56
     والغ
    0.44
     σου
    0.43
     وكذلك
    0.41
    akh
    0.41
     Liefer
    0.41
     Versicher
    0.41
    ian
    0.40
    px
    0.40
    Player
    0.40
    Activations Density 0.001%

    No Known Activations