© 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. 143374
    Prev
    Next
    INDEX
    Explanations

    there are

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

    numbers and specific items

    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
    為了
    0.49
    читы
    0.48
    тельством
    0.46
    ї
    0.46
    三百
    0.45
    靜
    0.45
    賺
    0.44
    祹
    0.43
    𝗌
    0.43
    伝統
    0.42
    POSITIVE LOGITS
     cedar
    0.55
     woody
    0.54
     Cedar
    0.53
     Aspen
    0.52
     Westbrook
    0.52
     weekend
    0.51
     Saturn
    0.51
     sunny
    0.51
     cast
    0.50
     shore
    0.50
    Activations Density 0.001%

    No Known Activations