© 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. 105566
    Prev
    Next
    INDEX
    Explanations

    I have a

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

    let's say you have

    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
     USING
    0.49
     Bonjour
    0.48
     же
    0.46
     Instead
    0.45
     მაშინ
    0.45
    のない
    0.45
    т
    0.44
     Selon
    0.44
     Chỉ
    0.43
     menggunakan
    0.43
    POSITIVE LOGITS
     surnames
    0.44
     sparsim
    0.41
    یثیت
    0.41
    有两个
    0.41
     ситуации
    0.41
     bowling
    0.39
    要去
    0.39
     finisher
    0.38
    ᱟ
    0.38
     hashTable
    0.38
    Activations Density 0.008%

    No Known Activations