© 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. 30993
    Prev
    Next
    INDEX
    Explanations

    grant numbers and codes

    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
     Kompon
    -0.85
    PIX
    -0.82
    Sequencing
    -0.82
    并未
    -0.81
     podía
    -0.79
     évaluations
    -0.79
     Ruhm
    -0.77
     cơ
    -0.77
    EndTag
    -0.77
     Klavier
    -0.77
    POSITIVE LOGITS
     grant
    1.49
     Grant
    1.36
    grant
    1.13
    Grant
    1.10
     No
    1.08
     grants
    1.07
     number
    1.06
     no
    1.05
     №
    0.94
     Nos
    0.92
    Activations Density 0.030%

    No Known Activations