© 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. 104439
    Prev
    Next
    INDEX
    Explanations

    for followed by specific words

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

    even or problems

    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
    Ph
    0.47
     actionable
    0.46
    ath
    0.45
    Wallet
    0.45
    Tham
    0.42
    '
    0.42
    ariest
    0.42
    athar
    0.41
    adav
    0.40
     humbling
    0.40
    POSITIVE LOGITS
     przez
    0.51
     于
    0.49
    BINARY
    0.48
     Morrison
    0.47
     মন
    0.47
    神奇
    0.47
     forças
    0.47
     وحتى
    0.47
    いたり
    0.46
     diferenças
    0.46
    Activations Density 0.000%

    No Known Activations