© 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. 251121
    Prev
    Next
    INDEX
    Explanations

    Australian Chinese Chinese Korean Russian German German Russian Chinese Portuguese

    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
     rigidity
    0.44
    elian
    0.42
     mạng
    0.42
     embers
    0.40
    ¨
    0.40
     cadence
    0.39
    arı
    0.39
     rocker
    0.39
    ("@
    0.38
    erde
    0.38
    POSITIVE LOGITS
    avanja
    0.48
     APIDC
    0.44
     플
    0.43
    蛋白質
    0.41
    葲
    0.40
    поте
    0.40
    SCIENCE
    0.40
    hatiti
    0.39
    вена
    0.39
    펍
    0.39
    Activations Density 0.001%

    No Known Activations