© 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. 161967
    Prev
    Next
    INDEX
    Explanations

    actor names and roles

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

    stamina bar, dry lips, streamlit

    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
     Fiberglass
    0.54
     Examination
    0.52
     Microbiology
    0.50
     Locate
    0.49
     TAE
    0.49
     Sketch
    0.48
    िखर
    0.48
    ᅭ
    0.47
    Examination
    0.46
    CommonAncestor
    0.46
    POSITIVE LOGITS
                    
    0.59
                     
    0.55
         
    0.51
    deaths
    0.51
     destaque
    0.50
    اي
    0.50
    ieden
    0.50
    stash
    0.48
    ’
    0.47
    death
    0.46
    Activations Density 0.002%

    No Known Activations