© 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. 30618
    Prev
    Next
    INDEX
    Explanations

    deduction is allowed

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

    negation or foreign text

    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
     thee
    0.47
     Sale
    0.41
    صف
    0.40
     intr
    0.40
    תי
    0.40
    클
    0.40
    单击
    0.40
    퐶
    0.40
     a
    0.39
    繁
    0.39
    POSITIVE LOGITS
     нельзя
    0.48
     везде
    0.46
    eşit
    0.46
     професси
    0.46
    Hud
    0.45
    ikir
    0.45
     serupa
    0.45
     nécessaire
    0.45
     জাহান
    0.45
     ரசிக
    0.44
    Activations Density 0.000%

    No Known Activations