© 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. 49076
    Prev
    Next
    INDEX
    Explanations

    web links and content

    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
     genio
    -1.00
    inum
    -0.89
    gering
    -0.84
     Technologie
    -0.84
     bois
    -0.83
    角色
    -0.82
     رم
    -0.81
     endfor
    -0.81
    XIV
    -0.81
    یک
    -0.80
    POSITIVE LOGITS
     (@
    1.04
    </blockquote>
    0.93
     (_.
    0.87
     tweets
    0.86
     heridos
    0.77
     tranh
    0.76
    sellors
    0.76
     обозна
    0.75
     houve
    0.75
    retweet
    0.74
    Activations Density 0.001%

    No Known Activations