© 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. 13-GEMMASCOPE-2-RES-16K
    7. 4890
    Prev
    Next
    INDEX
    Explanations

    boiling water, beating ingredients

    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_13_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
     desert
    0.92
    垟
    0.89
     hoff
    0.82
    堌
    0.80
     landfill
    0.79
    ilibus
    0.79
    ক্টো
    0.79
    閇
    0.79
    Ӏо
    0.79
     hilltop
    0.77
    POSITIVE LOGITS
     very
    0.86
    pxy
    0.83
     дуже
    0.82
     очень
    0.80
    際は
    0.79
    時
    0.78
    並且
    0.78
    very
    0.77
    $;
    0.77
     Pg
    0.77
    Activations Density 0.000%

    No Known Activations