© 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. 104760
    Prev
    Next
    INDEX
    Explanations

    public health organizations

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

    matrix divided by

    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
     foe
    0.52
    or
    0.50
    rose
    0.50
    ѕ
    0.50
    і
    0.50
    un
    0.48
    vis
    0.48
    Is
    0.48
     is
    0.48
    fluence
    0.48
    POSITIVE LOGITS
    工作的
    0.48
    机的
    0.47
    仂
    0.46
    额外的
    0.45
    椁
    0.45
     घोषणा
    0.45
    傲
    0.44
    碱
    0.43
    녈
    0.43
    珢
    0.43
    Activations Density 0.002%

    No Known Activations