© 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. 57759
    Prev
    Next
    INDEX
    Explanations

    scope carbon emissions

    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
    SUCCEEDED
    -0.72
     obtainable
    -0.70
    ipelago
    -0.70
     érté
    -0.69
    maxn
    -0.69
     wypeł
    -0.69
    はは
    -0.69
     proceeded
    -0.68
     Hamlin
    -0.68
    avares
    -0.67
    POSITIVE LOGITS
     Scope
    2.09
    Scope
    1.91
     scope
    1.82
    scope
    1.75
    Scopes
    1.70
     scopes
    1.58
    scopes
    1.45
    SCOPE
    1.34
     SCOPE
    1.30
     Sco
    1.16
    Activations Density 0.003%

    No Known Activations