© 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. 33934
    Prev
    Next
    INDEX
    Explanations

    you will dare

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

    choose one

    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
     apertura
    0.49
    രാജ
    0.48
     d
    0.47
     le
    0.46
    ையைப்
    0.45
     già
    0.45
    ibilità
    0.45
     реаги
    0.45
     as
    0.44
    __.
    0.44
    POSITIVE LOGITS
     사고
    0.45
     Ј
    0.43
    𒁺
    0.43
    ссия
    0.42
     బాల
    0.41
     गोली
    0.41
     जम
    0.41
     Gelände
    0.40
    なんか
    0.40
     forbindelse
    0.40
    Activations Density 0.000%

    No Known Activations