© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 7844
    Prev
    Next
    INDEX
    Explanations

    kimono, clothing, startup, regulations, students, Weimar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forte
    1.02
    zeichnung
    1.02
     possibile
    1.02
     recuperación
    1.01
     automaticamente
    1.01
    ありません
    1.01
     renovación
    1.00
    <unused1728>
    1.00
    <unused2204>
    1.00
     automáticamente
    1.00
    POSITIVE LOGITS
    生
    0.93
    また
    0.91
     क्विंट
    0.81
     terd
    0.80
    いて
    0.80
    ים
    0.79
     const
    0.78
     Pickle
    0.77
     इंत
    0.76
    𝒆
    0.75
    Activations Density 0.002%

    No Known Activations