© 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. 31248
    Prev
    Next
    INDEX
    Explanations

    journal abbreviations

    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
    Another
    -1.05
    ウンサー
    -0.84
    Additional
    -0.83
    áles
    -0.82
    What
    -0.82
    𝙬
    -0.76
    くな
    -0.75
    Sob
    -0.75
     ModelRenderer
    -0.74
    říve
    -0.73
    POSITIVE LOGITS
     Propulsion
    0.89
     Geng
    0.84
     Sms
    0.81
     Vascular
    0.78
     propulsion
    0.75
     Prey
    0.75
     tactile
    0.75
     Noun
    0.74
     iCloud
    0.74
    ICH
    0.74
    Activations Density 0.016%

    No Known Activations