© 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. 62749
    Prev
    Next
    INDEX
    Explanations

    collocations

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

    composite number

    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
    ettings
    0.48
    adhat
    0.46
    మో
    0.45
    и
    0.44
    ابية
    0.44
    мпа
    0.42
    궂
    0.42
    天堂
    0.41
    तो
    0.41
    చ్
    0.41
    POSITIVE LOGITS
     recept
    0.48
     potent
    0.48
     opa
    0.48
     niche
    0.48
     receita
    0.48
     recetas
    0.47
     যন্ত্র
    0.47
     美術
    0.46
     каме
    0.46
     packaging
    0.46
    Activations Density 0.000%

    No Known Activations