© 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. 74103
    Prev
    Next
    INDEX
    Explanations

    phrases starting with As or But

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

    good storySatoshiDOTrinse

    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
    es
    0.56
     october
    0.56
    con
    0.55
    ors
    0.55
     importance
    0.54
    inds
    0.52
    ate
    0.51
     \
    0.51
    ation
    0.50
    ments
    0.50
    POSITIVE LOGITS
    toluene
    0.48
    끔
    0.47
    ികള്‍
    0.47
    槍
    0.47
     permitió
    0.47
    ழுத
    0.46
     چیک
    0.45
    ডেইলি
    0.44
    deployRoot
    0.44
    
    0.44
    Activations Density 0.001%

    No Known Activations