© 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. 153815
    Prev
    Next
    INDEX
    Explanations

    public opinion

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

    public condemnation and outrage

    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
     หยุด
    0.42
    危险
    0.42
    워크
    0.42
    纹
    0.42
    รู้จัก
    0.41
    liver
    0.40
    FZ
    0.40
    📑
    0.40
    ┣
    0.40
     encouragement
    0.39
    POSITIVE LOGITS
     unpopular
    0.63
     publics
    0.62
     rakyat
    0.62
    民眾
    0.57
    народ
    0.56
     जनता
    0.55
     públicas
    0.54
     மக்களின்
    0.54
     optics
    0.52
     국민
    0.52
    Activations Density 0.145%

    No Known Activations