© 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. 66842
    Prev
    Next
    INDEX
    Explanations

    security, presence, cost, peptides, anxious, techniques, confidence, decisions, services, join

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

    use / exploitation / both

    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
     همچنین
    0.52
     nonché
    0.50
     murderous
    0.49
     solche
    0.47
    𝖗
    0.45
     සහ
    0.45
     cland
    0.45
     veja
    0.44
     albo
    0.44
     continuando
    0.44
    POSITIVE LOGITS
     BOTH
    0.40
    获取
    0.39
    [
    0.37
    '''
    0.37
    Под
    0.37
    ές
    0.37
    icación
    0.37
    过程
    0.37
    Вы
    0.36
     ALL
    0.36
    Activations Density 0.298%

    No Known Activations