© 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. 89836
    Prev
    Next
    INDEX
    Explanations

    final verdict and postmortem will

    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
    T
    0.56
    ne
    0.55
    é
    0.53
     nore
    0.52
     permanecer
    0.49
    Car
    0.49
    Terror
    0.49
    A
    0.48
     permite
    0.48
     continúa
    0.48
    POSITIVE LOGITS
    $&$-
    0.49
    mimeTypes
    0.45
     LongNumber
    0.45
     單
    0.45
     這個
    0.44
    >\<^
    0.42
    蘋果
    0.42
    샥
    0.42
    ಹಿ
    0.42
    Ⴀ
    0.42
    Activations Density 0.000%

    No Known Activations