© 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. 16119
    Prev
    Next
    INDEX
    Explanations

    ingredients

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

    ingredients:

    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
     publicaciones
    0.50
     campagnes
    0.49
     políticas
    0.47
     campañas
    0.45
    يمق
    0.44
     wisata
    0.44
    เซีย
    0.44
    ಙ
    0.43
     político
    0.42
     guerras
    0.42
    POSITIVE LOGITS
     ingredients
    1.66
    ingredients
    1.52
     Ingredients
    1.46
     ингреди
    1.37
     ingredientes
    1.36
     ingred
    1.33
    Ingredients
    1.32
     ingrédients
    1.32
     ingredient
    1.31
    食材
    1.30
    Activations Density 0.233%

    No Known Activations