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. 22-GEMMASCOPE-2-RES-16K
    4. 18
    Prev
    Next
    INDEX
    Explanations

    negative visualization, intercourse, seeding, chest

    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_22_width_16k_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
    .
    1.04
    ,
    0.89
    -
    0.89
     -
    0.87
    ↵↵
    0.86
    '
    0.82
    ’
    0.81
    ?
    0.76
    i
    0.75
    !
    0.74
    POSITIVE LOGITS
    𒅀
    0.99
    𐱃
    0.98
    𒆪
    0.96
    𒋢
    0.95
    <unused600>
    0.95
    𐰴
    0.94
    𒅗
    0.94
    arrerol
    0.93
     motionProxy
    0.93
    𐰖
    0.92
    Activations Density 10.958%

    No Known Activations