© 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. 55147
    Prev
    Next
    INDEX
    Explanations

    campaign following Clinton

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

    paths, believing, resisting, kitchens, streaming

    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
     argues
    0.50
    acă
    0.48
    ือบ
    0.47
     acara
    0.47
     haue
    0.46
    COMANDA
    0.46
    𝔪
    0.43
     closeup
    0.43
     Close
    0.42
    날
    0.42
    POSITIVE LOGITS
    屋外
    0.45
    褐色
    0.45
     نار
    0.44
     عمران
    0.43
     салы
    0.43
     الإلكتر
    0.43
     జో
    0.43
     бассей
    0.41
    ラックス
    0.41
     حبي
    0.41
    Activations Density 0.000%

    No Known Activations