© 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. 237473
    Prev
    Next
    INDEX
    Explanations

    sorting algorithms

    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
    繼
    0.48
    現代
    0.46
    超
    0.45
     defaulted
    0.45
     picked
    0.45
    共通
    0.44
    现代
    0.44
     seeded
    0.44
    缺
    0.43
    區
    0.42
    POSITIVE LOGITS
    useful
    0.49
     работ
    0.47
    rather
    0.46
     television
    0.46
     funniest
    0.46
    ar
    0.44
     loudspeaker
    0.44
     самое
    0.44
     escritor
    0.44
     writers
    0.44
    Activations Density 0.003%

    No Known Activations