Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 18665
    Prev
    Next
    INDEX
    Explanations

    asking questions to refine

    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
     discussion
    0.42
     circumstances
    0.42
     combinations
    0.41
     discussions
    0.40
     DETAILS
    0.39
     matchmaking
    0.39
     Z
    0.39
     availability
    0.39
     temptation
    0.39
     transgression
    0.39
    POSITIVE LOGITS
    are
    0.55
    Why
    0.53
    Is
    0.52
    s
    0.51
    is
    0.50
    Are
    0.47
    southeast
    0.47
    c
    0.47
    institute
    0.46
    old
    0.46
    Activations Density 0.047%

    No Known Activations