© 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. 150293
    Prev
    Next
    INDEX
    Explanations

    serving or containers

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

    constructive approach, acceleration vector, market conflict, previous version

    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
    啊
    0.45
    any
    0.43
    using
    0.43
    情绪
    0.42
    ç
    0.42
    精准
    0.41
    爱
    0.41
    becca
    0.40
    밌
    0.40
    λα
    0.40
    POSITIVE LOGITS
     impractic
    0.46
     retarded
    0.44
     craindre
    0.42
     automl
    0.39
     elution
    0.39
     dominions
    0.39
     لکھنے
    0.39
     exempted
    0.39
     interstices
    0.39
     outset
    0.38
    Activations Density 0.001%

    No Known Activations