© 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. 136853
    Prev
    Next
    INDEX
    Explanations

    supports them or heals

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

    largest, film, frequently, great

    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
     magnesium
    0.55
     ember
    0.53
     hog
    0.51
     vene
    0.49
     solenoid
    0.49
    </h6>
    0.48
     {$
    0.48
     ${\
    0.47
     maus
    0.47
     MgO
    0.47
    POSITIVE LOGITS
    Voor
    0.55
    Applications
    0.55
    Saat
    0.54
    추
    0.53
     المكتب
    0.51
    clerotic
    0.50
    antwoord
    0.50
    Dalam
    0.50
    Buffers
    0.49
    Tickets
    0.49
    Activations Density 0.000%

    No Known Activations