© 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. 181045
    Prev
    Next
    INDEX
    Explanations

    part of condition

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

    multi-lingual concepts

    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
    今回の
    0.46
     Tiki
    0.45
    सायनिक
    0.44
     arbejde
    0.44
    自
    0.44
     Hydro
    0.42
     Efter
    0.41
    |}\
    0.40
     आगामी
    0.40
     yearning
    0.40
    POSITIVE LOGITS
     गू
    0.46
    loci
    0.44
    mic
    0.43
     звезд
    0.42
     ಮತ
    0.41
     प्लीज
    0.41
     матри
    0.41
     मैदान
    0.40
     பண்ப
    0.40
     microw
    0.40
    Activations Density 0.000%

    No Known Activations