© 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. 52553
    Prev
    Next
    INDEX
    Explanations

    closing punctuation or quotation

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

    level, surface, status, interest

    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
    ająca
    0.46
    पास
    0.43
    कूट
    0.43
    Kale
    0.41
    лма
    0.40
    饗
    0.40
    ரும்பு
    0.40
    사와
    0.39
    कु
    0.39
    Hearts
    0.39
    POSITIVE LOGITS
     mode
    0.57
     sifatida
    0.51
     (-)
    0.50
     (+)
    0.50
    モード
    0.50
     તરીકે
    0.47
     شدن
    0.47
     (.)
    0.47
    である
    0.46
     ness
    0.46
    Activations Density 0.012%

    No Known Activations