© 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. 70023
    Prev
    Next
    INDEX
    Explanations

    speak for themselves

    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
     ‘‘
    -1.51
    :
    -1.44
    <bos>
    -1.36
     on
    -1.30
    回目の
    -1.28
     According
    -1.26
     ”
    -1.26
    ↵
    -1.21
     „
    -1.20
     voulu
    -1.17
    POSITIVE LOGITS
     any
    1.53
    }]{
    1.47
     now
    1.44
     può
    1.34
     اللجنة
    1.33
     until
    1.29
     bekende
    1.29
    ője
    1.28
     numerosi
    1.27
    новение
    1.27
    Activations Density 0.085%

    No Known Activations