© 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. 223260
    Prev
    Next
    INDEX
    Explanations

    stories that people remember

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

    Sustainability, rules, locker digit

    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
    ’
    0.49
     elucidate
    0.47
     mendapat
    0.46
    ،
    0.46
    Х
    0.45
     renders
    0.45
    しますが
    0.45
     cataracts
    0.45
     caves
    0.44
     silhouettes
    0.44
    POSITIVE LOGITS
    stocked
    0.50
    嗽
    0.49
    ohms
    0.48
    rakt
    0.48
    mêmes
    0.48
    iffness
    0.48
    es
    0.47
    wb
    0.47
    sembled
    0.47
    mau
    0.47
    Activations Density 0.001%

    No Known Activations