© 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. 4391
    Prev
    Next
    INDEX
    Explanations

    null checks

    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
     but
    0.89
     แต่
    0.70
     including
    0.68
     pero
    0.68
     maar
    0.65
    ;
    0.64
    ；
    0.64
    .;
    0.63
     using
    0.63
    แต่
    0.63
    POSITIVE LOGITS
    ByDefault
    0.78
    itative
    0.67
     mesenchymal
    0.66
    When
    0.66
     precluded
    0.66
     dissipative
    0.65
     сахар
    0.65
    when
    0.64
    ശി
    0.64
    persistent
    0.64
    Activations Density 0.086%

    No Known Activations