© 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. 129195
    Prev
    Next
    INDEX
    Explanations

    departure, months, Kardashian, season, photography, benefit

    np_acts-logits-general · gemini-2.5-flash-lite

    discussion and explanation

    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
     Terrorism
    0.44
    s
    0.43
    setError
    0.41
     Calls
    0.39
    线路
    0.39
     Infants
    0.38
    석
    0.38
    си
    0.38
     rigging
    0.38
     Arguments
    0.38
    POSITIVE LOGITS
     काढून
    0.54
     ayatan
    0.53
     disfrutar
    0.51
     phir
    0.51
     douleur
    0.50
     mutlu
    0.50
     yoki
    0.50
     joli
    0.49
     rupam
    0.49
     ponctué
    0.49
    Activations Density 0.000%

    No Known Activations