© 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. 34-GEMMASCOPE-RES-131K
    7. 32227
    Prev
    Next
    INDEX
    Explanations

    allows you to interact

    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_34/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
     annum
    -1.43
     hitherto
    -1.38
    Whilst
    -1.19
     whilst
    -1.15
     Whilst
    -1.12
    istisch
    -1.10
     bespoke
    -1.09
     ought
    -1.09
     thence
    -1.08
    genöss
    -1.04
    POSITIVE LOGITS
     your
    1.76
     you
    1.41
     dovr
    1.34
     możesz
    1.27
    your
    1.26
    
    1.20
     möglicherweise
    1.19
     erhi
    1.17
     }^{*}$
    1.17
     dirit
    1.16
    Activations Density 0.177%

    No Known Activations