© 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. 32845
    Prev
    Next
    INDEX
    Explanations

    your / our primary concept

    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
     own
    0.47
    PC
    0.46
    公司
    0.45
     eigenen
    0.45
    е
    0.44
     Own
    0.43
    ገድ
    0.42
    and
    0.42
    Own
    0.41
    AS
    0.40
    POSITIVE LOGITS
     yukarı
    0.52
     analyte
    0.51
     original
    0.46
     highlighted
    0.44
     indicator
    0.42
    刚才
    0.42
     protagonista
    0.41
     originality
    0.41
     tadi
    0.41
     예
    0.41
    Activations Density 0.044%

    No Known Activations