© 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. 222297
    Prev
    Next
    INDEX
    Explanations

    category Home section

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

    structured list formatting

    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
    ႇ
    0.49
    (
    0.48
    -
    0.48
     sostegno
    0.48
    Fees
    0.47
    AI
    0.47
     défendre
    0.46
     popolazione
    0.46
     defending
    0.44
     n
    0.44
    POSITIVE LOGITS
     ríg
    0.46
    óri
    0.45
     нашим
    0.45
     लम्
    0.44
     наше
    0.44
    utar
    0.44
    tLogRow
    0.44
    메라
    0.43
    鸬
    0.42
    డ్డు
    0.42
    Activations Density 0.001%

    No Known Activations