© 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. 13612
    Prev
    Next
    INDEX
    Explanations

    start of sentences or clauses

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

    justify further, how to

    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
    tl
    0.52
     通常
    0.49
    s
    0.49
    <0x9E>
    0.48
    ndale
    0.48
     povr
    0.47
    ms
    0.47
    <0x9F>
    0.46
    sı
    0.46
    sType
    0.46
    POSITIVE LOGITS
    ای
    0.49
     ایمان
    0.46
     deletions
    0.44
    omorphisms
    0.43
    篤
    0.42
    ongen
    0.42
    ບ
    0.42
    뤄
    0.42
    ینگ
    0.41
    یه
    0.41
    Activations Density 0.000%

    No Known Activations