© 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. 33708
    Prev
    Next
    INDEX
    Explanations

    Calls for us to act

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

    complex explanations preceded by conjunctions

    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
    {
    0.49
     భాగంగా
    0.42
    叮
    0.42
    Lessons
    0.42
    lessons
    0.42
    अ
    0.42
     ξεκ
    0.41
    LAUNCH
    0.41
    orientation
    0.40
     transporte
    0.40
    POSITIVE LOGITS
     Hölder
    0.47
     decipher
    0.46
    瞒
    0.45
     subjug
    0.45
     materialistic
    0.44
     beware
    0.43
     dieses
    0.43
     atleast
    0.43
     ihre
    0.42
     তবুও
    0.42
    Activations Density 0.001%

    No Known Activations