© 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. 186543
    Prev
    Next
    INDEX
    Explanations

    states and actions

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

    country names followed by for

    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
     新
    0.51
    出来
    0.50
     快
    0.47
     但
    0.46
    <0x89>
    0.46
     Beacon
    0.46
     大
    0.45
    います
    0.45
    urgo
    0.45
    但
    0.44
    POSITIVE LOGITS
    lara
    0.51
    fice
    0.49
    komen
    0.49
    e
    0.49
    ادى
    0.48
    उनकी
    0.48
    trends
    0.48
    hitung
    0.47
     anci
    0.47
    ائيه
    0.47
    Activations Density 0.000%

    No Known Activations