© 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. 168154
    Prev
    Next
    INDEX
    Explanations

    mathematical and foreign terms

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

    silly or ridiculous descriptions

    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
    ,
    0.50
    2
    0.48
    de
    0.48
    tre
    0.48
    才知道
    0.46
    taking
    0.46
    大
    0.45
    桐
    0.45
    ai
    0.45
    le
    0.44
    POSITIVE LOGITS
     الات
    0.54
     geometria
    0.53
     hepin
    0.52
     evidencias
    0.52
     المعادلات
    0.51
     caratteristiche
    0.50
     Ευ
    0.50
    ட்டிக்
    0.49
     avances
    0.49
     entrop
    0.49
    Activations Density 0.002%

    No Known Activations