© 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. 162008
    Prev
    Next
    INDEX
    Explanations

    date and month specific terms

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

    press release services

    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
     项目
    0.56
     Zeitschr
    0.55
    abbanti
    0.54
     Portug
    0.52
    㝡
    0.51
     通过
    0.51
     لع
    0.51
     vorm
    0.50
     bénéf
    0.50
     başlı
    0.50
    POSITIVE LOGITS
    지
    0.52
    f
    0.50
    defined
    0.48
    δικ
    0.46
    date
    0.46
    ';
    0.45
    Shield
    0.44
    D
    0.44
    );
    0.43
    R
    0.42
    Activations Density 0.000%

    No Known Activations