© 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. 88200
    Prev
    Next
    INDEX
    Explanations

    heard of, end of

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

    business, legal, and technical terms

    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
     j
    0.51
     J
    0.49
     Kamera
    0.48
    j
    0.45
    geber
    0.42
     THEY
    0.41
    懾
    0.41
     kamera
    0.40
     Camera
    0.40
     Në
    0.40
    POSITIVE LOGITS
    的な
    0.50
    ു
    0.50
    пози
    0.48
    heds
    0.48
    пин
    0.48
     رای
    0.47
    پ
    0.47
    وصل
    0.47
    PositionY
    0.47
    строй
    0.47
    Activations Density 0.001%

    No Known Activations