© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2054
    Prev
    Next
    INDEX
    Explanations

    obsidian ppv method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
     pulls
    0.70
    ɪ
    0.65
     प्रोवाइड
    0.65
     proposto
    0.65
    ૫
    0.62
     prospects
    0.62
    பிற
    0.61
    Provides
    0.61
     mq
    0.61
     Belf
    0.61
    POSITIVE LOGITS
    oshin
    0.69
     sufrido
    0.65
     решений
    0.64
    Ỡ
    0.63
    ন্নত
    0.62
     IGP
    0.62
     ül
    0.62
    ienta
    0.61
    阶段
    0.61
    clinical
    0.61
    Activations Density 1.943%

    No Known Activations