© 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. 145993
    Prev
    Next
    INDEX
    Explanations

    linking technical terms and definitions

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

    lists of numbered/bulleted items

    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
    ಪ
    0.51
    自从
    0.46
    Ко
    0.45
    Depuis
    0.43
    forming
    0.43
    자
    0.42
    م
    0.42
    Más
    0.42
    const
    0.42
    After
    0.41
    POSITIVE LOGITS
     отри
    0.52
     ගැනීම
    0.51
    प्रयोग
    0.50
     Fhir
    0.50
     keterangan
    0.49
    ("|"+"
    0.49
     করিয়াছিলেন
    0.48
     মোকাবে
    0.48
     সকলের
    0.48
    ATG
    0.47
    Activations Density 0.000%

    No Known Activations