© 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. 191815
    Prev
    Next
    INDEX
    Explanations

    conversations with men, FTP port

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

    understanding negative states

    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
     dwind
    0.52
     🎉
    0.52
     ATV
    0.52
     EPFO
    0.50
     patri
    0.50
    پيديا
    0.50
    🗼
    0.49
     Paytm
    0.49
     向
    0.48
     Zhong
    0.48
    POSITIVE LOGITS
    다
    0.50
    0
    0.47
    FS
    0.46
    لت
    0.45
    SOCK
    0.43
    دا
    0.43
    תו
    0.43
    <h6>
    0.42
    ারে
    0.42
    เก
    0.41
    Activations Density 0.001%

    No Known Activations