© 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. 200201
    Prev
    Next
    INDEX
    Explanations

    phrases following specific tokens

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

    understanding social situations

    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
    цией
    0.47
     Polity
    0.47
    炲
    0.45
     vardır
    0.45
     રાજ્ય
    0.44
     రాజ
    0.44
     Cinematic
    0.44
    трибу
    0.43
     депутат
    0.43
     बनर्जी
    0.43
    POSITIVE LOGITS
    魚
    0.47
     tyrosine
    0.46
     nutrient
    0.46
     enzim
    0.46
     biochem
    0.44
     fish
    0.44
    森
    0.42
     salmon
    0.41
     nutr
    0.41
     phyt
    0.41
    Activations Density 0.000%

    No Known Activations