© 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. 101804
    Prev
    Next
    INDEX
    Explanations

    cultivating researchers

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

    Turbo models

    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
    э
    0.47
     Torr
    0.44
     Sams
    0.44
    消化
    0.43
    леты
    0.41
     Transforms
    0.41
     niveles
    0.41
    笑道
    0.40
    颧
    0.40
     levels
    0.40
    POSITIVE LOGITS
     ナ
    0.59
     ಡ
    0.54
    ૩
    0.52
     continent
    0.51
     کر
    0.50
     і
    0.49
     มูล
    0.48
    ።
    0.48
    continent
    0.48
     കൂടുത
    0.48
    Activations Density 0.000%

    No Known Activations