© 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. 62824
    Prev
    Next
    INDEX
    Explanations

    dates and names

    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
     most
    -1.20
     their
    -1.19
     had
    -1.02
     or
    -1.02
     went
    -1.01
     consistently
    -1.00
     several
    -1.00
     made
    -0.99
     because
    -0.99
     came
    -0.98
    POSITIVE LOGITS
     Dinas
    1.20
    你不要
    1.20
     delightfully
    1.15
    焌
    1.13
    particularly
    1.12
     quintessential
    1.11
     unn
    1.11
    primarily
    1.10
    küche
    1.09
    訁
    1.09
    Activations Density 0.007%

    No Known Activations