© 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. 66805
    Prev
    Next
    INDEX
    Explanations

    appears before 'times'

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

    numbers with 2

    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
    م
    0.70
    는데
    0.66
    ن
    0.64
    𝙋
    0.62
     Más
    0.60
     اع
    0.59
     potenti
    0.59
    ر
    0.59
    Rés
    0.59
    Während
    0.57
    POSITIVE LOGITS
    í
    0.61
    iline
    0.57
    २०
    0.55
    い
    0.52
    ]$;
    0.51
    </h2>
    0.51
    v
    0.50
    á
    0.49
    ilen
    0.48
     कैरेट
    0.48
    Activations Density 0.094%

    No Known Activations