© 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. 34-GEMMASCOPE-RES-131K
    7. 106971
    Prev
    Next
    INDEX
    Explanations

    F# code or syntax

    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
     đính
    -0.74
    膈
    -0.72
     ácido
    -0.71
     grasping
    -0.70
    胰
    -0.70
    باح
    -0.69
    是非常
    -0.68
    荀
    -0.67
    adé
    -0.66
     oval
    -0.66
    POSITIVE LOGITS
    Microsoft
    0.96
     Microsoft
    0.90
    paramref
    0.83
     Emilia
    0.82
    Msg
    0.81
    <_>
    0.81
     крестьян
    0.81
     Mahat
    0.80
    :>
    0.79
     Fable
    0.78
    Activations Density 0.026%

    No Known Activations