© 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. 102147
    Prev
    Next
    INDEX
    Explanations

    children, research, reproduction

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

    followed by descriptive phrase

    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
     airs
    0.54
     obu
    0.50
    <unused1089>
    0.50
     oxyd
    0.50
    劶
    0.50
     assailant
    0.49
     Tsun
    0.48
     bosques
    0.48
     arrêter
    0.48
    आरआई
    0.48
    POSITIVE LOGITS
    го
    0.46
    pathetic
    0.46
    ص
    0.45
    やっと
    0.44
    幾乎
    0.43
    ocere
    0.42
    長的
    0.42
    ب
    0.42
    bere
    0.42
    每個
    0.42
    Activations Density 0.000%

    No Known Activations