© 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. 180705
    Prev
    Next
    INDEX
    Explanations

    plan followed by insurance, medical, or political terms

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

    teeming with potential

    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
    bouw
    0.52
    يت
    0.52
    粖
    0.51
    chnen
    0.48
    cyj
    0.47
    კ
    0.47
    노
    0.47
    wC
    0.47
    profissional
    0.46
    遜
    0.46
    POSITIVE LOGITS
     pokies
    0.46
     duplic
    0.46
     යුතු
    0.45
     dispensary
    0.44
     preachers
    0.44
     dividend
    0.44
    ்
    0.44
     preaching
    0.43
     proactive
    0.42
     mesothelioma
    0.42
    Activations Density 0.001%

    No Known Activations