© 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. 164073
    Prev
    Next
    INDEX
    Explanations

    critical status review priority

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

    sequence of

    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
     Wesley
    0.59
     Flight
    0.55
     Fleet
    0.51
     Khaled
    0.49
     Liner
    0.49
     Caramel
    0.49
     흘
    0.49
     Vincent
    0.49
     MHD
    0.48
     Winf
    0.48
    POSITIVE LOGITS
    >
    0.51
     wieder
    0.50
    Dere
    0.50
    tree
    0.49
    爭
    0.49
    before
    0.47
    FACT
    0.47
     rendu
    0.46
    љу
    0.46
    factual
    0.46
    Activations Density 0.001%

    No Known Activations