© 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. 174766
    Prev
    Next
    INDEX
    Explanations

    directions on

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

    controlled within Europe

    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
     दस्तावे
    0.55
    ドア
    0.49
    itação
    0.43
    洋
    0.42
    🥫
    0.42
    ವಾದ
    0.42
    🖖
    0.42
    ブレー
    0.42
    PLAIN
    0.42
     تھی
    0.42
    POSITIVE LOGITS
    лектро
    0.47
    ন্দ্র
    0.44
     conclude
    0.44
    quarters
    0.44
    _________
    0.44
     solucionar
    0.44
     ersch
    0.43
    三星
    0.42
     enanti
    0.42
     reso
    0.42
    Activations Density 0.000%

    No Known Activations