© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 33983
    Prev
    Next
    INDEX
    Explanations

    MQTT topics and subscriptions

    np_acts-logits-general · gemini-2.5-flash-lite

    updates, subscriptions, publishing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    兇
    0.52
     షూ
    0.50
    椪
    0.47
    泊
    0.47
     द्वार
    0.46
    鱉
    0.46
    žne
    0.45
     靴
    0.45
    譴
    0.45
    荸
    0.45
    POSITIVE LOGITS
     subscriptions
    0.86
     subscription
    0.81
     subscribing
    0.81
    订阅
    0.77
     subscribe
    0.74
     notifies
    0.73
     subscribed
    0.73
     Subscription
    0.72
     구독
    0.72
    subscribe
    0.72
    Activations Density 0.017%

    No Known Activations