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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 925
    Prev
    Next
    INDEX
    Explanations

    active/passive voice or states

    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_13_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
    relevant
    0.71
     onsite
    0.69
    bicycle
    0.68
    ↵
    0.67
    Bitte
    0.66
     akci
    0.66
    situ
    0.65
    Refer
    0.64
    Currently
    0.64
    Esta
    0.63
    POSITIVE LOGITS
     Mood
    0.76
    <0xF3>
    0.70
    лко
    0.68
     Communications
    0.66
    رير
    0.66
     Middle
    0.66
     Nothing
    0.64
     distinctions
    0.63
     “
    0.63
    ல்ல
    0.63
    Activations Density 0.000%

    No Known Activations