© 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. 163715
    Prev
    Next
    INDEX
    Explanations

    economic and legal analysis

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

    budget ranges and growth

    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
    vih
    0.45
     توا
    0.45
     participe
    0.44
    ៦
    0.43
     సాం
    0.43
     wen
    0.42
     gew
    0.41
     partecipare
    0.41
     ዋና
    0.41
     birbir
    0.40
    POSITIVE LOGITS
    뗑
    0.48
    effects
    0.46
     dioc
    0.45
    জম
    0.45
    releases
    0.45
    statements
    0.45
    ꒱
    0.43
    analysis
    0.43
    activation
    0.43
     folic
    0.43
    Activations Density 0.000%

    No Known Activations