© 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-16K
    7. 12607
    Prev
    Next
    INDEX
    Explanations

    market share and industry parts

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

    live streaming platforms

    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_16k_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
     DMR
    0.50
     listrik
    0.46
     среды
    0.46
     डाइ
    0.46
     tecnologie
    0.45
    紮
    0.44
     সহায়তা
    0.43
    羙
    0.43
    钥匙
    0.43
    ্ডিং
    0.42
    POSITIVE LOGITS
    n
    0.55
    p
    0.53
    the
    0.49
    indexOf
    0.48
    i
    0.48
    aux
    0.46
    g
    0.46
    break
    0.45
    require
    0.45
    %(
    0.44
    Activations Density 0.034%

    No Known Activations