© 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. 166274
    Prev
    Next
    INDEX
    Explanations

    before meals

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

    dig, game, World, verb, fats

    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
     حول
    0.60
    т
    0.59
    त
    0.56
     वर्ल्ड
    0.55
     ухуд
    0.54
     Ш
    0.54
     इतर
    0.53
     Violent
    0.53
     поги
    0.52
    et
    0.51
    POSITIVE LOGITS
    受到
    0.50
    DON
    0.44
    DIN
    0.44
    }
    0.44
    Dig
    0.43
    DIG
    0.42
    iqu
    0.41
    DN
    0.41
    不像
    0.41
    是你
    0.40
    Activations Density 0.002%

    No Known Activations