© 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. 117320
    Prev
    Next
    INDEX
    Explanations

    academic citations and section markers

    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
    Calculated
    -0.84
    hamel
    -0.80
    الخ
    -0.80
     operatives
    -0.79
     //
    -0.77
     berat
    -0.76
     duster
    -0.76
     holand
    -0.75
    сль
    -0.75
    ственно
    -0.75
    POSITIVE LOGITS
     שלנו
    1.12
    Proceedings
    1.04
     our
    0.97
     reviewers
    0.95
     však
    0.92
    \|_{
    0.92
     ablation
    0.90
    Experiments
    0.89
    our
    0.88
     handcrafted
    0.88
    Activations Density 0.027%

    No Known Activations