© 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. 184056
    Prev
    Next
    INDEX
    Explanations

    established, occurs, includes, terminates

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

    Hyper-Profiling

    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
     escoger
    0.52
    textFont
    0.50
    issait
    0.48
     बघेल
    0.48
    á
    0.48
     ventaja
    0.47
    YB
    0.47
    ieht
    0.46
    ų
    0.46
     л
    0.46
    POSITIVE LOGITS
    毫无
    0.48
     Golds
    0.48
     Reuse
    0.47
    மை
    0.46
     jin
    0.46
     volum
    0.45
     recycle
    0.44
     recycl
    0.43
     uop
    0.43
     upload
    0.43
    Activations Density 0.001%

    No Known Activations