© 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. 59064
    Prev
    Next
    INDEX
    Explanations

    addition and subtraction

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

    sums and calculations

    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
     ∣
    0.40
    朋友們
    0.39
    á
    0.38
     प्राइम
    0.38
    ậu
    0.38
     ▪
    0.37
     ஐந்து
    0.37
    誅
    0.37
     pequeña
    0.36
     ขนาด
    0.36
    POSITIVE LOGITS
    হইয়া
    0.43
     tambah
    0.42
     თვით
    0.41
     tessuto
    0.41
     jurisprudence
    0.41
     cittam
    0.41
     insinu
    0.40
     continua
    0.39
     oyo
    0.39
     effusion
    0.39
    Activations Density 0.000%

    No Known Activations