© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128492
    Prev
    Next
    INDEX
    Explanations

    surveys and reports

    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_22/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
     our
    -2.48
     you
    -1.51
    Our
    -1.50
     we
    -1.49
     unseren
    -1.30
    我們
    -1.27
     vokal
    -1.25
     tutup
    -1.24
    我们
    -1.23
     your
    -1.22
    POSITIVE LOGITS
    (()=>
    1.26
     allegedly
    1.21
     reportedly
    1.21
     mainly
    1.20
     variously
    1.20
     treated
    1.16
     variety
    1.13
    問い合わせ
    1.13
     scheinen
    1.13
     págs
    1.13
    Activations Density 0.230%

    No Known Activations