© 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. 107804
    Prev
    Next
    INDEX
    Explanations

    writers, consent, Switzerland

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

    deliberate choices, night dinners

    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
    וק
    0.52
    lx
    0.51
    Irr
    0.48
    lL
    0.47
     Tengah
    0.44
    Y
    0.44
    цима
    0.43
    кті
    0.43
    linson
    0.43
    น
    0.43
    POSITIVE LOGITS
     pianist
    0.52
     procedimientos
    0.46
     بالټ
    0.46
    ſon
    0.45
    ोरेशन
    0.44
    如果要
    0.44
    PRODUCTS
    0.44
     اگر
    0.43
     blogger
    0.42
     Vaughan
    0.42
    Activations Density 0.001%

    No Known Activations