© 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. 1811
    Prev
    Next
    INDEX
    Explanations

    showing relation or state

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

    information across

    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
    ن
    0.53
    н
    0.45
    事項
    0.43
    洎
    0.42
     highland
    0.41
     More
    0.41
    ophiles
    0.40
    )}_{
    0.39
     mực
    0.39
    v
    0.39
    POSITIVE LOGITS
    𝖽
    0.58
    GradientPanel
    0.56
    fabrik
    0.54
    ƒ
    0.52
    ।
    0.52
    ⦕
    0.52
     debilitating
    0.51
    𝗎
    0.50
     Rusia
    0.49
    Flicky
    0.49
    Activations Density 0.000%

    No Known Activations