© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 168796
    Prev
    Next
    INDEX
    Explanations

    specifying concrete details

    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
    प्रा
    0.47
    यह
    0.46
    Кра
    0.46
    ท่าน
    0.45
    ંત
    0.44
    2
    0.43
    區域
    0.42
    ほか
    0.42
    Violation
    0.41
    🗝
    0.40
    POSITIVE LOGITS
     anges
    0.46
     camber
    0.45
     possibili
    0.45
     espect
    0.44
     sock
    0.44
     tendría
    0.43
     tener
    0.43
     advertised
    0.43
     sensibil
    0.42
     aberration
    0.42
    Activations Density 0.010%

    No Known Activations