© 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. 142086
    Prev
    Next
    INDEX
    Explanations

    list punctuation

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

    faith and trust

    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
    ów
    0.48
    的反
    0.47
     этой
    0.46
    uzu
    0.46
    ón
    0.45
     regroup
    0.44
    ū
    0.44
    还
    0.43
    ateria
    0.43
    ↥
    0.43
    POSITIVE LOGITS
    Local
    0.50
     দিল্লি
    0.47
     predominance
    0.46
     εμφ
    0.46
     εμφαν
    0.46
    LE
    0.45
     রয়ে
    0.45
     തന്റെ
    0.45
    resolvers
    0.45
     vâ
    0.44
    Activations Density 0.000%

    No Known Activations