© 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. 31173
    Prev
    Next
    INDEX
    Explanations

    actions and reducers

    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
    choices
    -0.79
    了一眼
    -0.77
     podium
    -0.72
     tabindex
    -0.72
     trouverez
    -0.71
     özel
    -0.71
    inescent
    -0.71
    weight
    -0.71
    ribusi
    -0.71
     Koh
    -0.70
    POSITIVE LOGITS
     actions
    1.44
     action
    1.40
     reducer
    1.23
    reducer
    1.20
    getAction
    1.17
     Actions
    1.16
    ToAction
    1.14
     selectors
    1.14
     Action
    1.13
     Reducer
    1.12
    Activations Density 0.052%

    No Known Activations