© 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. 14047
    Prev
    Next
    INDEX
    Explanations

    quotation marks followed by words

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

    multi-lingual with punctuation, quotes, and specific phrasing (e.g., 'as stated in')

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

    quotation marks

    np_max-act-logits · claude-4-5-sonnetTriggered by @skarne
    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
    ارف
    0.40
    벡
    0.39
     dilemma
    0.38
     epidemic
    0.38
     boulders
    0.38
     habitudes
    0.37
     chandeliers
    0.37
     nark
    0.37
     اد
    0.37
    یہ
    0.37
    POSITIVE LOGITS
    presumably
    0.64
     “[
    0.61
     включая
    0.58
     unspecified
    0.56
    “[
    0.54
     "[
    0.53
     รวมถึง
    0.52
    including
    0.52
     אך
    0.51
    "[
    0.50
    Activations Density 0.074%

    No Known Activations