© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13522
    Prev
    Next
    INDEX
    Explanations

    quotation and attribution

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

    ending quotes followed by attribution

    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_16k_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
     phrasing
    0.47
    Nathan
    0.45
     سلمان
    0.44
    지
    0.43
     رہتے
    0.42
     Nathan
    0.40
     ብዙ
    0.39
     विद्व
    0.38
    وله
    0.38
     divulgação
    0.38
    POSITIVE LOGITS
    a
    0.49
    en
    0.48
    un
    0.48
    apellido
    0.47
     SHALL
    0.46
     была
    0.45
    is
    0.45
    ள்ளார்
    0.44
     _{(
    0.44
    уна
    0.44
    Activations Density 0.030%

    No Known Activations