© 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. 251826
    Prev
    Next
    INDEX
    Explanations

    manual pdf download

    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
     เวอร์
    0.48
     ایسی
    0.44
    砒
    0.43
    ամ
    0.42
     DMSO
    0.42
    ப்பொரு
    0.42
     มาก
    0.41
     เฉล
    0.41
     waisted
    0.41
    etrically
    0.41
    POSITIVE LOGITS
    v
    0.53
    फिर
    0.50
     fron
    0.50
    然后再
    0.48
    Xi
    0.48
    Ú
    0.47
     Tum
    0.47
    keyboard
    0.46
     Drum
    0.46
    ডেম
    0.46
    Activations Density 0.000%

    No Known Activations