© 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. 5976
    Prev
    Next
    INDEX
    Explanations

    double-check

    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
     வைக்க
    0.71
     slings
    0.71
    isAssignableFrom
    0.71
    buster
    0.68
     attracted
    0.67
    except
    0.66
    攒
    0.64
     სას
    0.64
    xmax
    0.63
     قلنا
    0.63
    POSITIVE LOGITS
    ‌هایی
    0.70
     Creature
    0.67
    แล
    0.66
     тик
    0.66
    辣
    0.65
     جی
    0.65
    (".
    0.64
    这些
    0.64
    这就
    0.63
    นั้น
    0.63
    Activations Density 0.033%

    No Known Activations