© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 178577
    Prev
    Next
    INDEX
    Explanations

    inspired bystarts withmake yourhome game

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

    elect control switch

    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
    Negative Logits
     maatau
    0.61
     ಅಪಾಯ
    0.57
    abhavena
    0.55
     അന്വേഷ
    0.54
     اکنون
    0.54
    🛫
    0.54
     हमको
    0.53
    <unused73>
    0.53
     આપણે
    0.53
     GoObject
    0.52
    POSITIVE LOGITS
     be
    0.51
    Tec
    0.50
    节
    0.50
    ort
    0.48
    稀
    0.45
     the
    0.44
    eller
    0.44
    Dev
    0.44
    _
    0.44
     el
    0.43
    Activations Density 0.001%

    No Known Activations