© 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. 71868
    Prev
    Next
    INDEX
    Explanations

    excellent quality or bargain

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

    in-suite laundry

    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
    During
    0.59
    Durante
    0.54
    Grav
    0.50
    Secondo
    0.50
    น
    0.50
    י
    0.50
    É
    0.48
    لاعب
    0.48
    Designed
    0.48
    Ecco
    0.47
    POSITIVE LOGITS
     initi
    0.49
     mandat
    0.48
     canc
    0.47
     PDPN
    0.47
    ordelen
    0.46
     paradigm
    0.45
     bootstrapping
    0.45
     anx
    0.44
     crystallinity
    0.44
    糾
    0.44
    Activations Density 0.000%

    No Known Activations