© 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. 145944
    Prev
    Next
    INDEX
    Explanations

    photographed, photographed, photographs, Blogger

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

    moral panic, awareness, input

    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
    THRESHOLD
    0.51
    ABLES
    0.47
     ECONOM
    0.46
    ницу
    0.45
     AUTHORITY
    0.45
    ACING
    0.44
    perceptron
    0.44
    ⬜
    0.44
    reduce
    0.43
     WARRANT
    0.43
    POSITIVE LOGITS
     fotografías
    0.48
     sported
    0.47
     zdjęcia
    0.47
     Blogger
    0.45
     çocuk
    0.44
     hồn
    0.43
     നിന്ന
    0.42
     நானும்
    0.42
     photographed
    0.42
     colabor
    0.41
    Activations Density 0.000%

    No Known Activations