© 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. 172950
    Prev
    Next
    INDEX
    Explanations

    on the

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

    words following on

    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
     срок
    0.49
     உற்ச
    0.49
    sail
    0.45
     ввести
    0.44
    Fs
    0.44
     کند
    0.43
    <0xED>
    0.43
     клуб
    0.43
     Америки
    0.43
    იდ
    0.42
    POSITIVE LOGITS
    authored
    0.43
     ಹೇಗೆ
    0.43
     rightfully
    0.41
     behest
    0.41
     blaming
    0.41
     どう
    0.40
    whom
    0.39
     Za
    0.39
    卿
    0.39
     NAG
    0.38
    Activations Density 0.072%

    No Known Activations