© 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. 222793
    Prev
    Next
    INDEX
    Explanations

    kamera and reproductions

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

    ethno nationalism

    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
    MARKED
    0.50
    SLC
    0.49
    INUS
    0.48
    𝚌
    0.48
    WRITE
    0.47
    UGUST
    0.47
    YSIS
    0.47
    VEL
    0.46
     ইহাই
    0.45
    classlist
    0.45
    POSITIVE LOGITS
     menghadapi
    0.58
     Pey
    0.49
    uhan
    0.49
    '
    0.46
     pitching
    0.45
    uras
    0.45
     Kamera
    0.44
     kamera
    0.44
    aking
    0.43
    มอบ
    0.42
    Activations Density 0.001%

    No Known Activations