© 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. 125092
    Prev
    Next
    INDEX
    Explanations

    difference between numbers

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

    Dark & moody portraits

    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
     Фурга
    0.53
     सोमवार
    0.52
    ثنين
    0.52
    地震
    0.51
     الصحي
    0.50
    ما
    0.49
     很
    0.49
    退
    0.49
    無
    0.48
    Monday
    0.48
    POSITIVE LOGITS
     TDs
    0.49
    켰
    0.46
     Peck
    0.45
     Verst
    0.44
    </h3>
    0.43
    kubernetes
    0.43
     Lands
    0.42
     Annot
    0.42
     DAW
    0.42
    PE
    0.42
    Activations Density 0.000%

    No Known Activations