© 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. 77788
    Prev
    Next
    INDEX
    Explanations

    españ specific word endings

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

    not... but contrast

    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
    EX
    0.57
    PRO
    0.54
    Requires
    0.54
    TE
    0.52
    U
    0.52
    Tec
    0.52
    Voici
    0.52
    Pole
    0.50
    N
    0.50
    Di
    0.49
    POSITIVE LOGITS
    \}.
    0.50
     무료
    0.50
    ojas
    0.49
     inap
    0.49
     tathapi
    0.49
     españ
    0.48
    oya
    0.48
     oa
    0.47
    inia
    0.47
     imassa
    0.47
    Activations Density 0.000%

    No Known Activations