© 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. 188723
    Prev
    Next
    INDEX
    Explanations

    fiber cement

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

    multilingual outputs

    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
    狠狠
    0.44
     지구
    0.44
     얼마
    0.42
    林
    0.41
    泽
    0.41
     הש
    0.41
    ິກ
    0.41
     nghĩ
    0.40
    郑
    0.40
    토
    0.40
    POSITIVE LOGITS
     chromatographic
    0.51
     pertinentes
    0.48
     elastomers
    0.48
     muque
    0.48
     calidad
    0.48
     providing
    0.47
    emas
    0.47
     plasmids
    0.47
    ktiv
    0.46
     hochwert
    0.46
    Activations Density 0.002%

    No Known Activations