© 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. 116737
    Prev
    Next
    INDEX
    Explanations

    items, receiving, always, Family, switching, crystals

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

    feathers, family, language, fit, API

    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
    털
    0.55
     ayak
    0.54
    chées
    0.49
    負担
    0.49
     torno
    0.48
    úan
    0.47
    .。
    0.47
     pastes
    0.47
    횽
    0.47
     señales
    0.47
    POSITIVE LOGITS
     Therapeutic
    0.46
     Prevalence
    0.45
    mapKey
    0.44
     Insulin
    0.43
     Nigeria
    0.42
     {}>,
    0.42
    iid
    0.41
     fairway
    0.41
     Overall
    0.41
     पहिली
    0.41
    Activations Density 0.000%

    No Known Activations