© 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. 30331
    Prev
    Next
    INDEX
    Explanations

    you want to

    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
    finally
    -0.85
    ᴹ
    -0.84
     resulted
    -0.81
     try
    -0.81
     Tot
    -0.80
     want
    -0.80
     приводит
    -0.80
    fka
    -0.79
     was
    -0.77
     وتم
    -0.77
    POSITIVE LOGITS
     thereby
    1.55
     implicitly
    1.35
     بذلك
    1.23
     effectively
    1.19
     zároveň
    1.18
     създа
    1.17
     jednocześnie
    1.16
     indirectly
    1.14
     Effectively
    1.13
     Damit
    1.08
    Activations Density 0.053%

    No Known Activations