© 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. 202450
    Prev
    Next
    INDEX
    Explanations

    limited specific types

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

    starting new clauses or sentences

    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
    intah
    0.47
    었다
    0.45
     parser
    0.42
     بیچ
    0.42
    颢
    0.42
     vírus
    0.42
    䒽
    0.42
    ública
    0.41
    โ
    0.41
    issait
    0.41
    POSITIVE LOGITS
    limited
    0.50
    க்கொண்டு
    0.46
    ه‌ای
    0.46
    lambda
    0.45
     সীমিত
    0.45
    lam
    0.44
    ご了承ください
    0.44
    ווי
    0.43
    limit
    0.43
     amet
    0.42
    Activations Density 0.001%

    No Known Activations