© 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. 31752
    Prev
    Next
    INDEX
    Explanations

    language specific words

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

    crucial importance

    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
     Clusters
    0.49
     Yearbook
    0.46
     Biotechnology
    0.46
    .
    0.46
     Contemporary
    0.45
     Pathways
    0.44
    ileen
    0.42
     Innovations
    0.42
     Blossom
    0.42
     Topology
    0.42
    POSITIVE LOGITS
     vaš
    0.54
    आपको
    0.53
    אם
    0.52
     сколько
    0.51
     ваш
    0.49
     jums
    0.49
    㐄
    0.49
     будет
    0.48
     вашей
    0.48
    անակ
    0.48
    Activations Density 0.000%

    No Known Activations