© 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. 112318
    Prev
    Next
    INDEX
    Explanations

    sending out or away

    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
     ܙ
    -2.23
    }$
    -2.22
    釹
    -2.16
    艄
    -2.08
     gripping
    -2.06
    </em>
    -2.05
    你还
    -2.02
    ﹍﹍
    -2.00
     scarcely
    -1.99
    mpagne
    -1.98
    POSITIVE LOGITS
    Two
    2.16
    噚
    2.14
     Using
    2.11
    b
    2.11
    Three
    2.09
     Two
    2.05
     Providing
    2.03
    there
    2.02
     Sebuah
    2.00
     Does
    1.98
    Activations Density 0.003%

    No Known Activations