© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 110131
    Prev
    Next
    INDEX
    Explanations

    precisely, ownership, retains

    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
     hostage
    0.43
     kritis
    0.43
    :
    0.41
     interrupt
    0.40
    apagos
    0.40
     decouple
    0.39
     sorella
    0.39
     hostages
    0.38
    ことに
    0.38
     rescue
    0.38
    POSITIVE LOGITS
     levelled
    0.47
    ሞ
    0.46
    人民币
    0.46
    пись
    0.45
    、
    0.44
    图标
    0.43
    भाविक
    0.43
    皮
    0.43
    v
    0.42
    万里
    0.42
    Activations Density 0.003%

    No Known Activations