© 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. 14716
    Prev
    Next
    INDEX
    Explanations

    alphabet and letters

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

    alphabet letters

    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
    乡
    0.50
     entrevistas
    0.43
     consciente
    0.42
    鄉
    0.41
    świad
    0.41
    showerror
    0.41
    contentInset
    0.40
    窅
    0.40
    താണ
    0.40
     اثر
    0.40
    POSITIVE LOGITS
     Alphabet
    0.94
     alphabet
    0.93
     alphabetical
    0.92
     letters
    0.87
     Buchstaben
    0.86
    alphabet
    0.86
     Letters
    0.86
    字母
    0.85
     numbered
    0.84
     alphabetically
    0.84
    Activations Density 0.019%

    No Known Activations