© 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. 156688
    Prev
    Next
    INDEX
    Explanations

    things, irregularity, fall

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

    inspect, clothing, rides, historically, optimizing

    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
     福
    0.50
     落
    0.48
     学習
    0.47
     クラ
    0.46
     приме
    0.46
     вяза
    0.44
    アラ
    0.44
     Бүгенге
    0.44
    🗒
    0.44
     つい
    0.43
    POSITIVE LOGITS
    ล
    0.46
     energie
    0.46
     voltage
    0.46
     exodus
    0.44
     sky
    0.43
    Energ
    0.42
    उच्च
    0.42
    रोध
    0.41
     እ
    0.41
    เป็น
    0.41
    Activations Density 0.000%

    No Known Activations