© 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. 44200
    Prev
    Next
    INDEX
    Explanations

    just + subsequent word

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

    container or enclosing object

    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
      
    0.50
     ভূমি
    0.49
     Ogun
    0.46
     variants
    0.46
     Ook
    0.46
     backpack
    0.46
     Over
    0.45
     doomed
    0.45
     “
    0.45
     Tüm
    0.45
    POSITIVE LOGITS
    अमेर
    0.48
    🔢
    0.45
    ?',
    0.44
    넉
    0.44
    avacanam
    0.44
    ?')
    0.44
    샀
    0.43
    жении
    0.42
    MessageNow
    0.41
     памят
    0.41
    Activations Density 0.000%

    No Known Activations