© 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. 155691
    Prev
    Next
    INDEX
    Explanations

    describing actions and outcomes

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

    explaining requirements and outcomes

    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
    惭
    0.44
    夫妻
    0.42
    েষ
    0.41
    ilinear
    0.41
     அமைக்க
    0.41
    Chancellor
    0.41
    quantitative
    0.40
    цион
    0.40
    жку
    0.40
    茗
    0.39
    POSITIVE LOGITS
    SECURITY
    0.52
    PROTE
    0.49
    png
    0.48
     حفاظ
    0.48
     sailboats
    0.48
     gangsters
    0.47
     middlemen
    0.47
     cale
    0.46
     storing
    0.46
     BUT
    0.46
    Activations Density 0.000%

    No Known Activations