© 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. 181625
    Prev
    Next
    INDEX
    Explanations

    my methodology is

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

    abbreviations and acronyms

    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
     biomarkers
    0.46
     subtypes
    0.46
     ipotesi
    0.46
     ち
    0.44
     questionnaires
    0.43
     groceries
    0.43
    ینو
    0.42
     insurers
    0.42
    ients
    0.41
     inaccuracies
    0.41
    POSITIVE LOGITS
     is
    0.50
     abdominal
    0.50
    ?
    0.49
    ?!
    0.49
    ”?
    0.48
     lagoon
    0.48
    ?”
    0.47
    t
    0.47
     skoro
    0.46
    ？
    0.46
    Activations Density 0.004%

    No Known Activations