© 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. 105311
    Prev
    Next
    INDEX
    Explanations

    phrases indicating change or state

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

    weather and limitations

    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
    examination
    0.46
    י
    0.46
    append
    0.46
    hazardous
    0.45
    Similar
    0.45
    эр
    0.44
    ires
    0.44
    いたり
    0.44
    蘖
    0.44
    Minnesota
    0.43
    POSITIVE LOGITS
     BURE
    0.58
     genotypes
    0.54
     macarons
    0.52
     waf
    0.52
     DHCP
    0.52
     Zhao
    0.52
     enchant
    0.51
     Routing
    0.51
     VoIP
    0.51
     Bamboo
    0.50
    Activations Density 0.001%

    No Known Activations