© 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. 104534
    Prev
    Next
    INDEX
    Explanations

    specializes in quality

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

    chess notation

    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
    ologischen
    0.54
    ())){
    0.50
    IGNORE
    0.49
     установи
    0.48
    Одна
    0.48
     মস্তিষ্
    0.46
    ز
    0.46
     bunu
    0.46
     zehn
    0.46
     attacc
    0.46
    POSITIVE LOGITS
     Person
    0.47
     Inlet
    0.45
     Tourist
    0.45
    person
    0.44
    ergy
    0.43
     Multif
    0.42
    ；
    0.42
     Moran
    0.41
     Lines
    0.41
     Spent
    0.41
    Activations Density 0.002%

    No Known Activations