© 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. 16-GEMMASCOPE-2-RES-262K
    7. 33997
    Prev
    Next
    INDEX
    Explanations

    always happy, open, experimenting

    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_16_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
    ف
    0.61
    ला
    0.56
     deserial
    0.54
     OPCODE
    0.53
    ோ
    0.53
     कल
    0.51
    بعد
    0.51
    శి
    0.51
    дят
    0.50
    ਲ
    0.50
    POSITIVE LOGITS
    ro
    0.52
    tle
    0.50
    rous
    0.50
    cards
    0.48
    typen
    0.48
     estrogen
    0.47
    toxic
    0.47
    t
    0.47
    ção
    0.46
    cad
    0.46
    Activations Density 0.000%

    No Known Activations