© 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. 5525
    Prev
    Next
    INDEX
    Explanations

    bash script usage and variables

    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
    𝙤
    0.92
    𝙘
    0.88
    অগ্র
    0.81
    اہم
    0.80
    ثل
    0.80
    𝙜
    0.79
     বিষয়ে
    0.79
     thúc
    0.78
    𝙝
    0.78
    ❼
    0.77
    POSITIVE LOGITS
     Edith
    0.73
    ূল
    0.65
    Syn
    0.65
    play
    0.64
    World
    0.64
     приро
    0.64
    installation
    0.63
    Lady
    0.63
    playing
    0.62
     Lady
    0.62
    Activations Density 0.020%

    No Known Activations