© 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
    3. Gemma-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3351
    Prev
    Next
    INDEX
    Explanations

    export default

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_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
     đ
    0.70
     tâches
    0.70
    routerProps
    0.69
     Ersatz
    0.69
     tejido
    0.68
     होकर
    0.67
    atória
    0.67
    ígenes
    0.67
    ட்டிக்க
    0.66
     உத்தர
    0.66
    POSITIVE LOGITS
    ^{*}$-
    0.74
     class
    0.69
     tenfold
    0.69
    ]-\
    0.67
     coated
    0.63
     walking
    0.62
    샤
    0.62
     arm
    0.60
    矚
    0.60
    ]$.
    0.60
    Activations Density 0.072%

    No Known Activations