© 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. 10364
    Prev
    Next
    INDEX
    Explanations

    Ji Hao, Hugo Chavez

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

    system, leader, or narrative elements

    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
    髋
    0.63
    柽
    0.61
     våra
    0.60
    莴
    0.59
    缡
    0.58
    缐
    0.58
    醌
    0.58
    颞
    0.57
     পরিপ্রে
    0.57
    萜
    0.57
    POSITIVE LOGITS
     nodded
    0.64
     murderous
    0.63
     idiot
    0.59
     despicable
    0.59
     Ji
    0.59
     domine
    0.59
    ——
    0.59
     hehe
    0.59
     blushed
    0.57
     villa
    0.57
    Activations Density 0.022%

    No Known Activations