© 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. 138659
    Prev
    Next
    INDEX
    Explanations

    describing states or characteristics

    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
    5
    0.68
    4
    0.61
    2
    0.56
    7
    0.54
    6
    0.50
    ecos
    0.44
    льнявыя
    0.44
    PRINT
    0.43
    9
    0.43
    arnell
    0.43
    POSITIVE LOGITS
     Chaos
    0.50
     United
    0.49
     imposed
    0.46
     विभिन्न
    0.45
     జరిగింది
    0.45
    犹豫
    0.45
     Choosing
    0.44
    一个新的
    0.44
     Entity
    0.44
     הת
    0.43
    Activations Density 0.005%

    No Known Activations