© 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. 19980
    Prev
    Next
    INDEX
    Explanations

    next gen or month

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

    foreign language words

    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
     alltid
    0.50
    an
    0.48
     اپنے
    0.48
     bens
    0.47
     및
    0.45
    ahh
    0.45
    limit
    0.44
     সবসময়
    0.44
    께서
    0.44
     kunt
    0.44
    POSITIVE LOGITS
     ব্রিটেন
    0.46
    铷
    0.45
     औरत
    0.44
     осо
    0.44
     leptons
    0.44
    বাংলাদেশে
    0.43
     Испании
    0.42
     neutrinos
    0.41
     mère
    0.41
     brasileira
    0.41
    Activations Density 0.000%

    No Known Activations