© 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. 237424
    Prev
    Next
    INDEX
    Explanations

    early diagnosis, book esq

    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
     Veamos
    0.47
     Leibn
    0.46
     इं
    0.46
     وقلنا
    0.45
    弇
    0.45
     Petroleum
    0.45
     ჩვენ
    0.45
     공식
    0.43
    roje
    0.43
     കിട
    0.43
    POSITIVE LOGITS
    TI
    0.53
    M
    0.51
    ah
    0.51
    ethe
    0.49
    ';
    0.48
    '''
    0.47
    T
    0.47
     ';
    0.47
    HI
    0.46
    an
    0.46
    Activations Density 0.000%

    No Known Activations