© 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. 181643
    Prev
    Next
    INDEX
    Explanations

    Operational Budget

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

    blotting away excess

    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
     aphids
    0.45
    ჲ
    0.45
     reasoning
    0.44
     ecosystems
    0.44
     formatting
    0.44
     pyt
    0.43
    Drag
    0.43
     adware
    0.43
     asserting
    0.42
     cigarettes
    0.42
    POSITIVE LOGITS
    endor
    0.51
     продолжает
    0.51
    urent
    0.50
    
    0.50
    ent
    0.49
     основним
    0.49
    шою
    0.48
     більше
    0.48
     letz
    0.47
    leich
    0.47
    Activations Density 0.001%

    No Known Activations