© 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. 10298
    Prev
    Next
    INDEX
    Explanations

    abstract states and concepts

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

    abstract concepts and qualities

    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
     बुरे
    0.38
     (*
    0.38
     idk
    0.37
     ওরফে
    0.37
     ৭
    0.36
    如果是
    0.36
     Datei
    0.36
     flashy
    0.35
    ta
    0.35
     मीटिंग
    0.35
    POSITIVE LOGITS
     cuyas
    0.39
    <unused2206>
    0.38
     whose
    0.37
     теркәлүсез
    0.36
     interdependence
    0.36
     χρει
    0.35
    
    0.35
     waterfront
    0.34
     spanning
    0.34
     mennesker
    0.34
    Activations Density 0.256%

    No Known Activations