© 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. 37365
    Prev
    Next
    INDEX
    Explanations

    the drums, the Lord

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

    written communication for job applications

    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
     vendo
    0.47
     және
    0.45
    টি
    0.44
     kişiler
    0.43
     मिठाई
    0.41
     получится
    0.41
    喟
    0.41
     అలాగే
    0.41
    цкий
    0.41
    Paged
    0.41
    POSITIVE LOGITS
     ambitions
    0.48
     axioms
    0.48
     poets
    0.47
     praises
    0.44
     존재
    0.43
     coffers
    0.43
     reken
    0.42
     semblance
    0.42
    窮
    0.42
     untimely
    0.42
    Activations Density 0.000%

    No Known Activations