© 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. 126571
    Prev
    Next
    INDEX
    Explanations

    words and phrases

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

    qualifiers for size or intensity

    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
    Palm
    0.45
    Because
    0.45
    因为
    0.44
     or
    0.44
     entitle
    0.42
    Cal
    0.42
    Prom
    0.42
     a
    0.42
    "
    0.41
     день
    0.41
    POSITIVE LOGITS
     باقي
    0.53
     prépuce
    0.49
     продолжает
    0.49
     sparsim
    0.49
    êts
    0.48
     ketiga
    0.48
     restantes
    0.48
     나머
    0.47
     میراتھن
    0.47
     específ
    0.46
    Activations Density 0.002%

    No Known Activations