© 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. 27219
    Prev
    Next
    INDEX
    Explanations

    George R. R. Martin books

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

    company, find, time, scale, standing, rudder, using, is, up

    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
     thorough
    0.42
     fours
    0.39
     audioEngine
    0.37
    (";
    0.37
     nineties
    0.37
    errors
    0.36
     tekrar
    0.36
     camel
    0.35
     lit
    0.35
     careful
    0.35
    POSITIVE LOGITS
    இந்நிலையில்
    0.40
    㗆
    0.38
    ောက်
    0.38
     Intr
    0.38
    latego
    0.38
     रच
    0.38
     अधिकार
    0.37
    łada
    0.37
     Smack
    0.37
     jellem
    0.36
    Activations Density 0.011%

    No Known Activations