© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 87344
    Prev
    Next
    INDEX
    Explanations

    as of dates

    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
     is
    -2.27
    ;
    -2.17
     to
    -2.13
     only
    -2.06
     same
    -2.02
    =
    -2.02
    lo
    -1.95
    >
    -1.95
    }
    -1.94
     and
    -1.88
    POSITIVE LOGITS
    泐
    2.09
    شخص
    1.84
    𝗕
    1.82
     perſ
    1.76
     sés
    1.72
    Keterangan
    1.71
     paſſ
    1.65
     inond
    1.63
    Kemudian
    1.63
     คุณ
    1.63
    Activations Density 0.158%

    No Known Activations