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-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 1581
    Prev
    Next
    INDEX
    Explanations

    Okay, conversational starter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     imong
    0.58
    Do
    0.56
     ;,
    0.56
     ":
    0.56
     Rather
    0.56
     якобы
    0.55
    ன்றும்
    0.55
     Otherwise
    0.54
     Too
    0.53
    తి
    0.52
    POSITIVE LOGITS
     let
    1.27
     lets
    1.00
    !
    1.00
    hh
    0.98
    let
    0.93
     yes
    0.92
    hhh
    0.90
     yeah
    0.88
    hhhh
    0.87
     perfecto
    0.83
    Activations Density 0.434%

    No Known Activations