© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32307
    Prev
    Next
    INDEX
    Explanations

    in store for the future

    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
    ometric
    -0.74
    nall
    -0.73
     Reduce
    -0.71
     nutrientes
    -0.71
    словно
    -0.70
     mög
    -0.69
    afar
    -0.69
    τική
    -0.69
     períodos
    -0.68
    salm
    -0.68
    POSITIVE LOGITS
     store
    3.42
    store
    2.70
    Store
    2.58
     Store
    2.42
    STORE
    2.16
     STORE
    2.13
     stores
    1.95
     stored
    1.84
    getStore
    1.79
    stored
    1.59
    Activations Density 0.023%

    No Known Activations