© 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. 184642
    Prev
    Next
    INDEX
    Explanations

    daily routine, involves a, are not

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

    shame, freedom, country, sector

    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
    站
    0.53
    發生
    0.51
     Rentals
    0.51
     Optimization
    0.46
    iv
    0.46
    初始化
    0.45
    Popup
    0.44
    A
    0.44
     Stations
    0.44
     Galleries
    0.44
    POSITIVE LOGITS
    ็อก
    0.50
    ном
    0.49
     విజయ
    0.48
    ная
    0.48
    сун
    0.47
    𝚓
    0.47
    ㅈ
    0.46
    𝘫
    0.45
    рий
    0.45
    sı
    0.45
    Activations Density 0.000%

    No Known Activations