© 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. 36929
    Prev
    Next
    INDEX
    Explanations

    adequately protected

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

    problems, specific domains

    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
     之
    0.44
     이후
    0.43
     aktual
    0.42
    Subsequently
    0.42
     lud
    0.41
     Subsequent
    0.39
     válto
    0.38
    loten
    0.38
     hal
    0.38
     انت
    0.37
    POSITIVE LOGITS
    ם
    0.49
    ັດ
    0.48
    pregnancy
    0.46
    遜
    0.46
     partnering
    0.43
    ädchen
    0.43
    轅
    0.41
    ป่วย
    0.41
    走り
    0.41
    мс
    0.40
    Activations Density 0.000%

    No Known Activations