© 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. 98291
    Prev
    Next
    INDEX
    Explanations

    sleep, photos, mature, orders, choose, shipping

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

    diverse subjects like animals and AI

    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
    soluble
    0.45
    licensed
    0.43
    鎳
    0.43
    фикси
    0.42
    現
    0.42
     NSC
    0.42
    rubber
    0.42
    consumed
    0.42
     निर्म
    0.42
    высо
    0.42
    POSITIVE LOGITS
     ekonomik
    0.53
    aları
    0.52
     zabezpie
    0.50
     przede
    0.49
     rapidement
    0.48
     przes
    0.47
    잼
    0.47
     sizlerle
    0.47
    bardziej
    0.46
     způ
    0.46
    Activations Density 0.000%

    No Known Activations