© 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. 237617
    Prev
    Next
    INDEX
    Explanations

    too plus adjective

    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
     предотвра
    0.77
    ی
    0.75
     эффек
    0.73
     pozw
    0.71
     актива
    0.70
     установ
    0.70
    نتی
    0.68
     and
    0.67
    );//
    0.67
     достат
    0.66
    POSITIVE LOGITS
    ون
    1.12
    ii
    0.95
    pping
    0.89
    وم
    0.88
    ى
    0.88
    ot
    0.85
    ،
    0.83
    ide
    0.77
    ies
    0.77
    v
    0.76
    Activations Density 0.026%

    No Known Activations