© 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. 222855
    Prev
    Next
    INDEX
    Explanations

    service, art, collection, influence

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

    removing words or formatting

    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
     उलट
    0.47
     {:?}",
    0.46
     Pltf
    0.46
     二
    0.46
    ція
    0.45
     βρίσκεται
    0.44
     ὑ
    0.43
     υψη
    0.43
    ouette
    0.43
    oglobulin
    0.42
    POSITIVE LOGITS
    s
    0.56
     cír
    0.54
    است
    0.52
    سا
    0.49
    في
    0.48
    قر
    0.47
    Sunday
    0.47
    m
    0.47
     darken
    0.46
     oscuro
    0.46
    Activations Density 0.000%

    No Known Activations