© 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-65K
    7. 790
    Prev
    Next
    INDEX
    Explanations

    quotation marks followed by t, 2, 0, 1

    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_65k_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
    鉈
    0.49
    ньому
    0.48
    側
    0.48
     clause
    0.46
    让他
    0.46
     Clause
    0.46
     그는
    0.45
    ITIVE
    0.45
     childlike
    0.45
     कहा
    0.43
    POSITIVE LOGITS
    a
    0.47
    ,
    0.46
    ា
    0.45
    es
    0.45
    anded
    0.45
    व्ह
    0.44
     działalności
    0.44
    美品
    0.43
    dirs
    0.42
    CRUD
    0.42
    Activations Density 0.000%

    No Known Activations