© 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. 52146
    Prev
    Next
    INDEX
    Explanations

    emphasis punctuation

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

    loan payment calculations

    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
    ंनो
    0.49
     کاکروچ
    0.48
    뢨
    0.46
     berita
    0.45
     camadas
    0.45
     composants
    0.45
    лянчук
    0.45
     cadeaux
    0.45
    غط
    0.45
    ান্তরিত
    0.45
    POSITIVE LOGITS
    (
    0.53
    '
    0.51
    ove
    0.49
    s
    0.49
    ∉
    0.48
    ody
    0.48
    sby
    0.48
    us
    0.47
    ের
    0.46
     as
    0.46
    Activations Density 0.000%

    No Known Activations