© 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. 138083
    Prev
    Next
    INDEX
    Explanations

    not talking

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

    describing nouns like statue or app

    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
     voisins
    0.49
     السين
    0.45
     выбора
    0.44
     Schreiben
    0.43
     منتخب
    0.42
     soglas
    0.42
    埒
    0.41
     scelta
    0.41
    écution
    0.41
    ਗੇ
    0.40
    POSITIVE LOGITS
    ที่เป็น
    0.50
    মাত
    0.48
    ll
    0.47
    ylated
    0.47
    tting
    0.46
    touchstart
    0.45
    𝐥
    0.45
     दास
    0.44
     dawned
    0.44
    UiThread
    0.44
    Activations Density 0.001%

    No Known Activations