© 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. 10382
    Prev
    Next
    INDEX
    Explanations

    larger, smaller, higher, long, place, position

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

    specialized terminology, codes, or suffixes

    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
    CIÓN
    0.46
     клас
    0.46
     పి
    0.46
    楓
    0.45
    你会
    0.45
     комму
    0.43
     глу
    0.43
     охра
    0.43
     слегка
    0.42
     изме
    0.42
    POSITIVE LOGITS
    queries
    0.52
    afi
    0.51
    adi
    0.50
    free
    0.50
    rocks
    0.50
    mi
    0.49
     Wadi
    0.49
    م
    0.48
    adel
    0.48
    esses
    0.48
    Activations Density 0.000%

    No Known Activations