© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5197
    Prev
    Next
    INDEX
    Explanations

    words starting with "Per"

    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_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
     ADA
    0.72
    ದ
    0.63
    पण
    0.62
    タニ
    0.62
     telemedicine
    0.59
    谯
    0.59
    Finite
    0.59
    ͓
    0.59
    eki
    0.58
    ilizce
    0.57
    POSITIVE LOGITS
     Cobra
    0.64
     гру
    0.62
     Ove
    0.61
     मिळू
    0.61
     Cre
    0.60
     समृद्ध
    0.60
    ં
    0.60
     vom
    0.60
     miso
    0.59
     క్
    0.59
    Activations Density 0.130%

    No Known Activations