© 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. 168072
    Prev
    Next
    INDEX
    Explanations

    purchase and make

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

    demonstrate, photons, Transformers

    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
     magnitudes
    0.48
    igual
    0.44
    不管是
    0.41
     पहुंचते
    0.41
    涞
    0.41
    ൂരി
    0.40
    EXT
    0.40
    訫
    0.40
    考虑到
    0.40
    捭
    0.39
    POSITIVE LOGITS
    ]="
    0.49
     fez
    0.46
    を購入
    0.46
     Colored
    0.45
    colored
    0.45
     macaroni
    0.45
     acheté
    0.44
     condensate
    0.43
     quatre
    0.43
     quatro
    0.42
    Activations Density 0.003%

    No Known Activations