© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 243748
    Prev
    Next
    INDEX
    Explanations

    liability, generosity, sterility, courage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    钦
    0.53
     interesses
    0.49
    灿
    0.46
     økonom
    0.46
     económicas
    0.46
    联合国
    0.46
    經濟
    0.46
    স্বাধীন
    0.46
    经济
    0.45
    转变
    0.45
    POSITIVE LOGITS
     +
    0.54
     bandages
    0.54
     studded
    0.54
     m
    0.53
     cable
    0.51
    áo
    0.50
     clump
    0.49
     lute
    0.49
    lou
    0.48
     hauling
    0.48
    Activations Density 0.000%

    No Known Activations