© 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. 61683
    Prev
    Next
    INDEX
    Explanations

    federal government monitor

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

    . , ; ?

    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
     concetto
    0.46
     Conselho
    0.46
    䉍
    0.46
     pigeons
    0.45
    উল্লেখ্য
    0.44
     conceitos
    0.44
     பேசு
    0.43
     因為
    0.43
     Consejo
    0.43
    ល់
    0.42
    POSITIVE LOGITS
    a
    0.49
    5
    0.46
    monitor
    0.46
    6
    0.46
    OPH
    0.45
    na
    0.45
    cl
    0.44
     rematch
    0.44
     chromatography
    0.43
    监控
    0.43
    Activations Density 0.000%

    No Known Activations