© 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. 13311
    Prev
    Next
    INDEX
    Explanations

    abstract qualifiers and their domains

    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
    S
    0.83
    U
    0.83
     sogenannte
    0.82
     sogenannten
    0.77
    일
    0.76
    كي
    0.75
    quela
    0.73
    수
    0.73
    いい
    0.72
    り
    0.72
    POSITIVE LOGITS
    0.77
    ity
    0.73
     она
    0.59
     nudity
    0.57
    阌
    0.57
     resuscitation
    0.57
    ität
    0.56
    ITY
    0.56
    ॉजी
    0.55
    ্ড
    0.55
    Activations Density 0.296%

    No Known Activations