© 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. 203674
    Prev
    Next
    INDEX
    Explanations

    search completion

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

    tokenizer, lightweight, strike, 5 years

    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
    μων
    0.50
    فیر
    0.50
     পরবর্তীতে
    0.50
    وسیع
    0.48
    მიან
    0.48
    物体
    0.47
     پڑے
    0.46
    푦
    0.45
     двох
    0.44
    arses
    0.44
    POSITIVE LOGITS
     arrog
    0.53
     diz
    0.52
     conj
    0.49
    ्‍
    0.48
     busc
    0.48
     myster
    0.47
    स
    0.47
     describe
    0.46
     $(<
    0.46
     pronounce
    0.45
    Activations Density 0.000%

    No Known Activations