© 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. 20725
    Prev
    Next
    INDEX
    Explanations

    footnotes and citations

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

    punctuation, lists, examples

    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
    ANIES
    0.46
    Ⲥ
    0.42
    скую
    0.42
     iunie
    0.42
    ləşdirilib
    0.41
    lify
    0.41
    Asie
    0.41
    }_{-}\
    0.41
     ию
    0.41
    скими
    0.41
    POSITIVE LOGITS
     Alcohol
    0.44
     Scarlet
    0.43
     Chem
    0.43
     Canvas
    0.41
     Sir
    0.41
     Che
    0.40
     Quote
    0.40
      
    0.39
     Dialog
    0.39
     chem
    0.38
    Activations Density 0.006%

    No Known Activations