© 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. 134244
    Prev
    Next
    INDEX
    Explanations

    seasonal directions

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

    qualifying adjectives

    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
     Рей
    0.57
    вии
    0.55
    諱
    0.52
     produisent
    0.51
     仕事
    0.51
     kammam
    0.50
     heredit
    0.50
    蒐
    0.50
    بيع
    0.49
     провер
    0.49
    POSITIVE LOGITS
    CI
    0.47
    .".
    0.47
    Tempo
    0.45
    .'
    0.45
    Akt
    0.44
    ",
    0.43
    Season
    0.43
     Filament
    0.43
    Principal
    0.43
    encoder
    0.43
    Activations Density 0.001%

    No Known Activations