© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14874
    Prev
    Next
    INDEX
    Explanations

    positive attributes

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

    appropriate/suitable choice

    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_16k_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
     ব
    0.44
    焼け
    0.41
    來自
    0.41
     通常
    0.41
     Detta
    0.40
     Defaults
    0.39
    但这
    0.39
     }));
    0.39
    proud
    0.39
    採
    0.38
    POSITIVE LOGITS
     appealing
    0.57
     convenient
    0.57
     attractive
    0.57
    方便
    0.57
     conveniently
    0.57
    正好
    0.56
     suficientemente
    0.55
     ನನಗೆ
    0.55
     intéressante
    0.55
     interesting
    0.55
    Activations Density 0.401%

    No Known Activations