© 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. 242175
    Prev
    Next
    INDEX
    Explanations

    availability of options or procedures

    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
    και
    0.51
    which
    0.48
    ς
    0.48
    inaldo
    0.47
    っと
    0.46
    s
    0.46
    під
    0.45
    劇
    0.45
    sim
    0.44
    meniz
    0.44
    POSITIVE LOGITS
    ूबी
    0.47
     crece
    0.46
     diarrhoea
    0.45
     quail
    0.44
     الصحة
    0.44
    ల్యే
    0.44
    书城
    0.43
     lapply
    0.42
     intercourse
    0.42
    IUpdate
    0.42
    Activations Density 0.001%

    No Known Activations