© 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. 12218
    Prev
    Next
    INDEX
    Explanations

    numbers and articles

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

    relates to, connection, caused by, use of

    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
    ue
    0.54
    la
    0.52
     фараз
    0.47
    ﺓ
    0.47
    iece
    0.46
     سلس
    0.46
     इमर
    0.46
     редакти
    0.46
    ்ட
    0.46
    lad
    0.46
    POSITIVE LOGITS
     toddlers
    0.45
     pastor
    0.44
    ENV
    0.44
     minimal
    0.44
     babies
    0.43
    襁
    0.42
     pageant
    0.42
    מש
    0.41
     ENV
    0.41
     Spitzen
    0.41
    Activations Density 0.000%

    No Known Activations