© 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. 233868
    Prev
    Next
    INDEX
    Explanations

    thinking about costs

    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
     ترلاسه
    0.49
    匍
    0.47
     बिज़
    0.44
    可知
    0.43
     రాజ్యం
    0.43
    PHYS
    0.42
    បី
    0.42
    起始
    0.42
    精灵
    0.41
    thar
    0.41
    POSITIVE LOGITS
     bæ
    0.50
     누
    0.48
     breaches
    0.47
    åg
    0.47
     झ
    0.46
     हो
    0.46
     ਬ
    0.46
     מג
    0.45
    æ
    0.45
    작
    0.44
    Activations Density 0.001%

    No Known Activations