© 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. 17-GEMMASCOPE-2-RES-16K
    7. 4623
    Prev
    Next
    INDEX
    Explanations

    technical paths and commands

    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
     relevante
    0.77
     strengthen
    0.71
     hoofdst
    0.70
    `/
    0.69
    |");
    0.68
     relevant
    0.67
    本作
    0.67
     possibilities
    0.66
     strengthening
    0.66
    (`/
    0.66
    POSITIVE LOGITS
    imm
    0.73
     якобы
    0.70
    .*
    0.69
    imi
    0.69
     কেন্দ্রীয়
    0.69
    ill
    0.68
    aki
    0.67
    kl
    0.67
    idi
    0.67
    har
    0.66
    Activations Density 0.150%

    No Known Activations