© 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. 138980
    Prev
    Next
    INDEX
    Explanations

    our outreach

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

    soundtrack, journey, Milano, originally

    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
    з
    0.55
     তারপর
    0.48
    ق
    0.47
    Manuel
    0.47
     Basilica
    0.45
    ínguez
    0.45
    邀請
    0.45
     Istanbul
    0.45
    QUANT
    0.45
     नुकसान
    0.44
    POSITIVE LOGITS
    ᠯ
    0.45
    creens
    0.43
    iatric
    0.42
     collectibles
    0.41
     مقصد
    0.40
    sels
    0.40
    atious
    0.40
     تصل
    0.39
     polys
    0.38
     diameter
    0.38
    Activations Density 0.000%

    No Known Activations