© 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. 19748
    Prev
    Next
    INDEX
    Explanations

    think about

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

    explaining what something is

    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
     제한
    0.46
    都会
    0.45
     பெரும்பாலான
    0.43
     ክፍ
    0.42
     सभी
    0.42
     obstacles
    0.42
    雑
    0.42
    移行
    0.41
    芾
    0.41
     ಹೆಚ್ಚ
    0.41
    POSITIVE LOGITS
     enfin
    0.45
     infine
    0.43
     cancé
    0.41
     CANADA
    0.40
     épouse
    0.40
     scientifique
    0.39
     aonde
    0.39
    سین
    0.39
     vendu
    0.39
     lawfully
    0.38
    Activations Density 0.000%

    No Known Activations