© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86360
    Prev
    Next
    INDEX
    Explanations

    Geneva, Genoa, Gemini locations and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     are
    -2.58
     However
    -2.31
     We
    -2.30
     gemeinsame
    -2.22
     damaligen
    -2.19
    钲
    -2.16
     Großen
    -2.14
     pflegen
    -2.06
     suchen
    -2.03
     wahre
    -2.03
    POSITIVE LOGITS
     秋冬
    2.52
    the
    2.25
    ቍ
    2.25
     voud
    2.25
    who
    2.13
     pú
    2.11
     devotees
    2.06
    سجيلات
    2.05
     vois
    1.99
    DDDD
    1.98
    Activations Density 0.005%

    No Known Activations