© 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. 142059
    Prev
    Next
    INDEX
    Explanations

    Youth icon withheld travel bread most popular broadly best

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

    product liability certificate

    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
     óleo
    0.50
    经历了
    0.46
    愠
    0.46
     বেরিয়ে
    0.45
     rote
    0.45
    逘
    0.45
     grabación
    0.45
    响起
    0.44
     válida
    0.43
    СТЬ
    0.43
    POSITIVE LOGITS
    imi
    0.56
    iis
    0.52
    ij
    0.51
    x
    0.51
    iet
    0.50
    aniy
    0.50
    ice
    0.50
    ina
    0.50
    jt
    0.49
    yam
    0.49
    Activations Density 0.002%

    No Known Activations