© 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. 174864
    Prev
    Next
    INDEX
    Explanations

    actual patent

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

    lists of numbers, scientific terms

    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
     abstracto
    0.43
    agan
    0.43
     देखिएगा
    0.42
    <0x95>
    0.42
    CacheV
    0.42
     Caesar
    0.41
     সাপ্তাহ
    0.41
     やっぱり
    0.41
     တော့
    0.40
     प्रीवियस
    0.40
    POSITIVE LOGITS
     trong
    0.46
     değişken
    0.46
     equivalently
    0.46
    λιο
    0.46
    dll
    0.45
    ﺩ
    0.45
     disb
    0.44
    トゥ
    0.44
     dne
    0.44
     тю
    0.44
    Activations Density 0.000%

    No Known Activations