© 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. 35046
    Prev
    Next
    INDEX
    Explanations

    after words, punctuation

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

    Resume options

    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
     ситуацию
    0.52
     dissu
    0.49
     спра
    0.48
     попы
    0.47
     kiosks
    0.46
     verband
    0.45
     reconsider
    0.45
     論
    0.44
     situation
    0.44
     temporarily
    0.43
    POSITIVE LOGITS
    এরপর
    0.56
    তারপর
    0.52
    كل
    0.51
    খ
    0.48
    他的
    0.46
    ामान्य
    0.46
    یک
    0.45
     Spectroscopy
    0.45
    pound
    0.44
     Ended
    0.44
    Activations Density 0.000%

    No Known Activations