© 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. 238877
    Prev
    Next
    INDEX
    Explanations

    legal or technical terms

    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
    ní
    0.55
     \%
    0.54
     arte
    0.50
     \|\
    0.49
     vuos
    0.49
     ute
    0.49
     postseason
    0.48
    ORMAL
    0.48
     jsme
    0.47
     khan
    0.47
    POSITIVE LOGITS
    Variation
    0.49
     лінії
    0.48
    Harmony
    0.48
     линии
    0.47
     вариант
    0.46
    ხილ
    0.46
    حديث
    0.46
    ｉ
    0.46
    誇
    0.46
    צל
    0.45
    Activations Density 0.001%

    No Known Activations