© 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. 224609
    Prev
    Next
    INDEX
    Explanations

    quantities ordered

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

    valuable tool, demands obedience, locals often

    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
    რც
    0.50
     klein
    0.49
    க்கு
    0.48
    ഌ
    0.48
    гие
    0.47
    ит
    0.47
    бели
    0.47
    лле
    0.46
    た
    0.46
    гут
    0.45
    POSITIVE LOGITS
     เง
    0.51
     នៅ
    0.47
     conosc
    0.46
    Opens
    0.45
     نعرف
    0.44
     redan
    0.43
     רא
    0.42
     interi
    0.42
     رمضان
    0.41
     resetCounters
    0.41
    Activations Density 0.001%

    No Known Activations