© 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. 61206
    Prev
    Next
    INDEX
    Explanations

    buildings without

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

    specific acronyms and terms

    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
    ه
    0.49
     كيلو
    0.47
     كأس
    0.47
     بدل
    0.46
    جون
    0.46
    واد
    0.45
     герцо
    0.44
     γεγον
    0.44
    يو
    0.44
    鰐
    0.43
    POSITIVE LOGITS
    ät
    0.53
    inya
    0.52
    itt
    0.51
    aniya
    0.50
     disampaikan
    0.49
     uneas
    0.49
    gue
    0.48
    ogue
    0.48
    ally
    0.47
    gam
    0.47
    Activations Density 0.000%

    No Known Activations