© 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. 134687
    Prev
    Next
    INDEX
    Explanations

    package configuration

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

    organization, evaluation, specific American contexts

    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
     звезды
    0.43
     retali
    0.43
    Ф
    0.42
     gwiaz
    0.41
    Ã
    0.41
    كد
    0.40
    드
    0.40
     vengeance
    0.40
    MLS
    0.40
    Д
    0.40
    POSITIVE LOGITS
     nytt
    0.50
    abbanti
    0.46
    友好
    0.44
    newValue
    0.43
    novo
    0.43
    köz
    0.42
     reaff
    0.42
     bezieht
    0.41
     blijft
    0.40
    abhavam
    0.40
    Activations Density 0.001%

    No Known Activations