© 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. 112133
    Prev
    Next
    INDEX
    Explanations

    alphabet and letter activities

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

    alphabet and 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
    PREFIX
    0.50
    VW
    0.44
    Wh
    0.41
    坊
    0.41
    hljs
    0.40
    wh
    0.39
     斜
    0.39
    poke
    0.38
    rectangular
    0.38
    邸
    0.38
    POSITIVE LOGITS
     алфа
    0.57
     Buchstaben
    0.52
     Alphabet
    0.51
     alfabet
    0.50
     alfabeto
    0.50
     Letter
    0.49
     LETTER
    0.49
     CHARSET
    0.48
     letra
    0.46
     LETTERS
    0.46
    Activations Density 0.016%

    No Known Activations