© 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. 233679
    Prev
    Next
    INDEX
    Explanations

    think you, StateBeing, As part

    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
     got
    0.46
    言語
    0.46
     Jiří
    0.46
    ří
    0.45
     Pis
    0.43
     ヘ
    0.43
     அகத்திய
    0.43
     burrow
    0.43
    acher
    0.42
     uç
    0.42
    POSITIVE LOGITS
    막
    0.50
    N
    0.49
    Aluminum
    0.46
    needle
    0.44
     अह
    0.43
     सकें
    0.43
    X
    0.43
     आलम
    0.43
    XP
    0.42
    ἢ
    0.41
    Activations Density 0.001%

    No Known Activations