© 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-16K
    7. 12723
    Prev
    Next
    INDEX
    Explanations

    degrees and certificates

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

    multilingual content

    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
    ឿ
    0.43
     инг
    0.40
    OCE
    0.38
    dual
    0.36
     Ply
    0.36
     रुझ
    0.35
     ممل
    0.35
    assers
    0.34
    𒉌
    0.34
     allemaal
    0.33
    POSITIVE LOGITS
     Sixteen
    0.40
     Hé
    0.36
     Hfn
    0.36
     zon
    0.35
    íf
    0.35
    飭
    0.35
     Callahan
    0.34
    ambarkan
    0.34
    ุต
    0.33
    ounced
    0.33
    Activations Density 0.080%

    No Known Activations