© 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. 166219
    Prev
    Next
    INDEX
    Explanations

    language and specific terms

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

    focuses on suffering

    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
     静
    0.43
     później
    0.42
     ),
    0.40
     डेवल
    0.40
     Conserv
    0.40
     vremena
    0.40
     Circus
    0.40
     général
    0.39
     আত্মীয়
    0.39
     dém
    0.39
    POSITIVE LOGITS
     evidenced
    0.46
     పే
    0.46
     painfully
    0.45
    轪
    0.45
    Гра
    0.44
     төр
    0.44
    吝
    0.43
     লিখে
    0.43
    ដ៏
    0.42
    سل
    0.42
    Activations Density 0.002%

    No Known Activations