© 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. 40-GEMMASCOPE-2-RES-262K
    7. 27051
    Prev
    Next
    INDEX
    Explanations

    absolute neutrino mass

    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_40_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
     heuristic
    0.46
     heuristics
    0.45
    ABASE
    0.43
     特
    0.41
    Tecla
    0.41
    的話
    0.40
    ROS
    0.39
    LAT
    0.38
    TAINS
    0.38
    特
    0.38
    POSITIVE LOGITS
    omponent
    0.40
    beweg
    0.38
    ិន
    0.37
    ناسب
    0.36
    otten
    0.36
    医师
    0.36
    pract
    0.35
     ancien
    0.35
    arny
    0.35
    besch
    0.35
    Activations Density 0.000%

    No Known Activations