© 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. 35723
    Prev
    Next
    INDEX
    Explanations

    specific words preceding punctuation

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

    performance and goals

    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
    commands
    0.50
     to
    0.48
     commands
    0.48
     Commands
    0.47
    ↵↵
    0.46
     propositions
    0.45
     starts
    0.44
     is
    0.44
     エ
    0.44
     EPA
    0.43
    POSITIVE LOGITS
    𝙞
    0.58
    setKeepCallback
    0.55
    𝙪
    0.55
     wpły
    0.50
     trá
    0.50
    क्षकों
    0.50
     tráfico
    0.50
     thử
    0.49
     metabolismo
    0.49
     wú
    0.48
    Activations Density 0.001%

    No Known Activations