© 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. 23776
    Prev
    Next
    INDEX
    Explanations

    rear seats

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

    encoder-decoder, layer, led, down

    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
    ayon
    0.42
    ./
    0.42
    ...\
    0.41
    比起
    0.40
     マル
    0.40
    લી
    0.39
    ..\
    0.39
    न
    0.39
    コー
    0.38
     وتق
    0.38
    POSITIVE LOGITS
     possuem
    0.50
    шаем
    0.49
    йдз
    0.48
    ान्य
    0.45
     eloqu
    0.44
     compléter
    0.44
     langage
    0.44
     béton
    0.44
     leur
    0.43
     sexu
    0.43
    Activations Density 0.000%

    No Known Activations