© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13268
    Prev
    Next
    INDEX
    Explanations

    at mentions

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

    names after @

    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_16k_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
     hippocamp
    0.64
     hypothes
    0.63
    (
    0.63
     brou
    0.61
     duvet
    0.61
     epistle
    0.60
     incidente
    0.60
     bás
    0.59
     detour
    0.58
     appartamento
    0.58
    POSITIVE LOGITS
    to
    0.96
    na
    0.93
    no
    0.88
    f
    0.86
    re
    0.83
    x
    0.79
    ta
    0.79
    does
    0.78
    のは
    0.77
    não
    0.75
    Activations Density 0.029%

    No Known Activations