© 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. 109353
    Prev
    Next
    INDEX
    Explanations

    help assure you

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

    clarify, answer, fluid, positive

    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
    មើ
    0.49
    ajit
    0.46
    炼
    0.46
    ill
    0.45
    讨
    0.44
    aj
    0.44
    赖
    0.43
    嘚
    0.43
    ben
    0.42
    सी
    0.42
    POSITIVE LOGITS
    ី
    0.48
    がありますが
    0.48
     skirts
    0.46
    だが
    0.44
    itherto
    0.44
     buoyant
    0.44
    <unused614>
    0.42
     spongy
    0.42
     pinn
    0.42
    従来の
    0.41
    Activations Density 0.000%

    No Known Activations