© 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. 138921
    Prev
    Next
    INDEX
    Explanations

    Martian diameters

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

    avoid fancy formatting and images

    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
    ì
    0.52
    ê
    0.49
     관
    0.49
    ément
    0.46
     Autism
    0.45
     致
    0.44
    àm
    0.43
     보험
    0.43
     Focus
    0.43
     Slope
    0.42
    POSITIVE LOGITS
     sociedades
    0.48
     tyto
    0.48
     uzman
    0.47
    suitcase
    0.46
    validators
    0.46
     diarios
    0.46
     antiguas
    0.45
     extranjeros
    0.45
    েন্টস
    0.45
    म्स
    0.45
    Activations Density 0.001%

    No Known Activations