© 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. 88748
    Prev
    Next
    INDEX
    Explanations

    Silurian open Faw allergens link

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

    discrete packets

    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
    被害
    0.47
    posizione
    0.46
    クリーム
    0.46
    𝐁
    0.44
    ፨
    0.44
     TIMER
    0.44
    த்தில்
    0.43
    腟
    0.43
     entrambe
    0.43
     மண்
    0.42
    POSITIVE LOGITS
     is
    0.57
     Win
    0.55
     Atari
    0.55
     Comput
    0.51
     brems
    0.51
     seguros
    0.50
     has
    0.50
     Pontiac
    0.48
     laptop
    0.45
     Block
    0.44
    Activations Density 0.000%

    No Known Activations