© 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. 106632
    Prev
    Next
    INDEX
    Explanations

    SaaS, cloud, software, enterprise

    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
     KFC
    -0.79
     Collider
    -0.79
     OTP
    -0.78
     Butch
    -0.78
     Agra
    -0.76
    Slim
    -0.76
     حسن
    -0.76
    ombia
    -0.76
     Krug
    -0.75
    vés
    -0.73
    POSITIVE LOGITS
     SaaS
    2.25
     cloud
    2.08
     software
    1.86
     Software
    1.76
    Software
    1.73
    cloud
    1.70
     Cloud
    1.65
    software
    1.63
     subscription
    1.55
    Cloud
    1.47
    Activations Density 0.046%

    No Known Activations