© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 100617
    Prev
    Next
    INDEX
    Explanations

    potential for

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

    weapons and ideology

    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
     приня
    0.43
     тво
    0.42
    estellt
    0.42
    巨
    0.42
     приняли
    0.42
     تے
    0.41
    腌
    0.41
    堕
    0.41
     создании
    0.40
     цю
    0.40
    POSITIVE LOGITS
     indoors
    0.52
     unimportant
    0.49
     outdoors
    0.49
     aria
    0.48
    HTMLElement
    0.48
    l
    0.47
     bese
    0.46
     lev
    0.46
    នៅលើ
    0.44
    負荷
    0.44
    Activations Density 0.005%

    No Known Activations