© 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. 13122
    Prev
    Next
    INDEX
    Explanations

    dimensions and materials

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

    shapes and properties

    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
     yun
    0.41
     Marty
    0.41
    云
    0.39
    凯
    0.38
     croy
    0.38
    欺
    0.38
     गै
    0.37
     alkenyl
    0.37
     chapitre
    0.37
    肯
    0.36
    POSITIVE LOGITS
     धार
    0.44
    材質
    0.43
    ite
    0.42
     containing
    0.41
    ymmetrical
    0.40
     Generations
    0.40
     enthält
    0.40
     contains
    0.40
    கால
    0.39
     contiene
    0.39
    Activations Density 0.090%

    No Known Activations