© 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. 86546
    Prev
    Next
    INDEX
    Explanations

    just the

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

    specific highlights and details

    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
    ти
    0.55
    Monster
    0.51
    戞
    0.50
    表記
    0.50
    ة
    0.49
    ミー
    0.49
    ネル
    0.49
    フィルム
    0.48
    릭터
    0.48
    ừ
    0.48
    POSITIVE LOGITS
     lockdown
    0.52
     lockdowns
    0.52
     Sulawesi
    0.50
     convoy
    0.50
     Benzema
    0.48
     KIDS
    0.46
     harrowing
    0.46
     kids
    0.46
     Ovo
    0.46
     Lanzarote
    0.44
    Activations Density 0.003%

    No Known Activations