© 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. 52232
    Prev
    Next
    INDEX
    Explanations

    his + noun/verb

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

    words often followed by 'a' or 'the'

    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
     IVF
    0.47
    するとき
    0.46
     Academia
    0.44
    ურთიერთ
    0.44
     гораздо
    0.43
     reunited
    0.42
     గత
    0.42
    䀎
    0.42
     учас
    0.42
     факуль
    0.42
    POSITIVE LOGITS
    m
    0.60
    ing
    0.54
    p
    0.52
    be
    0.52
    l
    0.51
    platforms
    0.49
    n
    0.49
    standards
    0.49
    en
    0.49
    rot
    0.47
    Activations Density 0.000%

    No Known Activations