© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19609
    Prev
    Next
    INDEX
    Explanations

    stars and constellations in the sky

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
     нейтро
    0.56
    🪐
    0.56
     импуль
    0.53
    Physics
    0.51
    薩
    0.50
    Chromosome
    0.49
    彗
    0.49
    太阳
    0.46
     иссле
    0.45
    Cascade
    0.45
    POSITIVE LOGITS
     seen
    0.53
     evenings
    0.50
     daily
    0.47
     afternoons
    0.46
     Seen
    0.46
     nights
    0.45
     Advertising
    0.45
    seen
    0.44
     evening
    0.44
     afternoon
    0.43
    Activations Density 0.038%

    No Known Activations