© 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. 166735
    Prev
    Next
    INDEX
    Explanations

    common words followed by sentence components

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

    about nothing

    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
    .
    0.57
    _
    0.54
    ABLE
    0.54
    }
    0.51
    ULE
    0.50
    REL
    0.50
    UI
    0.47
    DIS
    0.47
     ⇒
    0.47
     kannst
    0.46
    POSITIVE LOGITS
    enciais
    0.52
     bernama
    0.50
     absurdity
    0.50
     sinister
    0.50
     iguais
    0.50
    axo
    0.46
    สอง
    0.45
    ênio
    0.45
    टर्न
    0.44
    枨
    0.44
    Activations Density 0.001%

    No Known Activations