© 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. 164841
    Prev
    Next
    INDEX
    Explanations

    Operations

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

    defied gravity

    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
     journaling
    0.45
    сан
    0.45
    pathy
    0.45
     registry
    0.44
    pulumi
    0.43
    тель
    0.43
    тов
    0.43
    ⣶
    0.43
    től
    0.43
    oxide
    0.42
    POSITIVE LOGITS
     이하
    0.54
     Pusat
    0.53
     xay
    0.50
     금액
    0.47
     Partei
    0.44
    航空公司
    0.44
     Aan
    0.43
    आईएस
    0.43
     محدود
    0.43
    葶
    0.43
    Activations Density 0.001%

    No Known Activations