© 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. 77215
    Prev
    Next
    INDEX
    Explanations

    alban, alb, alba variants

    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
     zweite
    -0.74
     ganze
    -0.73
     Stations
    -0.71
     articulated
    -0.71
     enthusi
    -0.71
     thus
    -0.71
    pagest
    -0.69
    ሔ
    -0.68
    țional
    -0.68
    stds
    -0.67
    POSITIVE LOGITS
     alb
    1.19
     Alb
    0.99
     Alba
    0.98
    ALB
    0.94
    egis
    0.91
     ALB
    0.90
    cete
    0.87
    alb
    0.85
     alba
    0.84
    Alb
    0.82
    Activations Density 0.024%

    No Known Activations