© 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. 53957
    Prev
    Next
    INDEX
    Explanations

    options, optional, choice

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

    optional

    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
     fabrica
    0.57
    ระบบ
    0.54
    ுகள்
    0.53
     phosphoryl
    0.53
     turbine
    0.52
    ร้าน
    0.51
     competency
    0.50
    ک
    0.50
    turbine
    0.49
    Мы
    0.49
    POSITIVE LOGITS
    н
    0.58
    的效果
    0.57
    íti
    0.55
    ;\
    0.55
     heutigen
    0.55
    als
    0.54
    ſ
    0.53
    íl
    0.52
    肮
    0.52
    ен
    0.51
    Activations Density 0.008%

    No Known Activations