© 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. 179571
    Prev
    Next
    INDEX
    Explanations

    posted in or on

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

    accessing URLs and python code

    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
    ᆨ
    0.46
     a
    0.45
     ur
    0.43
     teor
    0.42
     Philosophy
    0.41
    ↵↵
    0.40
    文章
    0.40
     philosophy
    0.39
     Philosoph
    0.39
    瞭
    0.39
    POSITIVE LOGITS
     молит
    0.52
     antennes
    0.50
    <unused34>
    0.50
    <unused49>
    0.49
    <unused27>
    0.48
     аутох
    0.48
     bơm
    0.47
     quarant
    0.47
     திரும்பி
    0.47
     हमने
    0.45
    Activations Density 0.001%

    No Known Activations