© 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. 90158
    Prev
    Next
    INDEX
    Explanations

    President Trump's

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

    arrival, chapter, override, voice

    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
     партне
    0.53
    hovah
    0.52
     partners
    0.50
    t
    0.48
     夜
    0.47
     populaires
    0.46
     rappers
    0.46
     काली
    0.45
     alkohol
    0.45
     ان
    0.45
    POSITIVE LOGITS
     خارجية
    0.46
     საქართველოს
    0.45
    ዎች
    0.45
    验
    0.44
     ruộng
    0.42
    Pennsylvania
    0.42
    㗁
    0.41
    的目标
    0.41
     الخارجية
    0.41
    olicy
    0.41
    Activations Density 0.002%

    No Known Activations