© 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. 161040
    Prev
    Next
    INDEX
    Explanations

    in sustainability and humiliation

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

    Arithmetic Logic Unit

    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
    ivore
    0.46
     دی۔
    0.45
     جوړونکی
    0.45
    çı
    0.40
    ۔
    0.40
     ত্যাগ
    0.39
     چاہیے۔
    0.39
    嗒
    0.39
     店
    0.39
    িকর
    0.39
    POSITIVE LOGITS
    voxel
    0.50
     tournée
    0.46
    Λ
    0.45
     وبي
    0.45
    a
    0.45
    জ
    0.45
    γρα
    0.44
     কাউন্স
    0.44
     convexes
    0.44
    шал
    0.43
    Activations Density 0.001%

    No Known Activations