© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 198573
    Prev
    Next
    INDEX
    Explanations

    OSX planning

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

    individual and others

    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
    透过
    0.49
     którego
    0.49
     enceinte
    0.49
     différente
    0.48
     humaine
    0.47
    Disponible
    0.46
    住房
    0.46
    Ę
    0.46
     humanoid
    0.45
    กระ
    0.45
    POSITIVE LOGITS
    vet
    0.45
    voc
    0.45
     vet
    0.43
     தனி
    0.43
    alter
    0.41
     demandas
    0.41
    avio
    0.41
    bet
    0.40
    anskrit
    0.40
     determinations
    0.40
    Activations Density 0.000%

    No Known Activations