© 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. 4969
    Prev
    Next
    INDEX
    Explanations

    technical commands and text generation

    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
    Idi
    0.77
    ணு
    0.74
     ইন্দুর
    0.74
    <unused123>
    0.72
    <unused1936>
    0.70
     Idi
    0.70
     multifaceted
    0.70
    <unused165>
    0.69
     Bly
    0.69
    <unused507>
    0.69
    POSITIVE LOGITS
    south
    0.80
    दक्षिण
    0.77
     SOUTH
    0.74
    f
    0.73
    ɑ
    0.73
     ask
    0.72
    মেজ
    0.72
     arrivé
    0.72
    ʏ
    0.72
    اگ
    0.71
    Activations Density 0.000%

    No Known Activations