© 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. 132678
    Prev
    Next
    INDEX
    Explanations

    political campaigns and policy changes

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

    network components

    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
    setBadgeText
    0.53
     ピアス
    0.50
    男生
    0.50
    drawString
    0.49
    блица
    0.49
    ಕ್ಸ್
    0.49
    𝕟
    0.48
    聡
    0.48
    𝗺
    0.48
    dplyr
    0.48
    POSITIVE LOGITS
     E
    0.46
     beat
    0.42
     profession
    0.42
     particip
    0.41
     infringe
    0.41
    ,
    0.41
     route
    0.40
     impeach
    0.40
     post
    0.40
     곧
    0.40
    Activations Density 0.001%

    No Known Activations