© 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. 210537
    Prev
    Next
    INDEX
    Explanations

    chiefs, tier, cart, evidence

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

    testigo único

    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
    años
    0.49
    胴
    0.48
    iado
    0.48
    mény
    0.48
    필
    0.47
    או
    0.47
    ܦ
    0.46
    ﾝ
    0.46
    𝗟
    0.46
    𝗙
    0.46
    POSITIVE LOGITS
     word
    0.47
     println
    0.45
     ruby
    0.45
     poplar
    0.44
    اونلو
    0.44
     kiwi
    0.43
     agreement
    0.43
     lyrics
    0.42
     song
    0.42
     fires
    0.42
    Activations Density 0.002%

    No Known Activations