© 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. 45415
    Prev
    Next
    INDEX
    Explanations

    multilingual text processing

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

    actions, states, or goals

    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
     evas
    0.49
     complement
    0.45
     其
    0.45
     gode
    0.44
     tended
    0.44
     如
    0.43
     truth
    0.43
     y
    0.42
     resa
    0.41
     heen
    0.41
    POSITIVE LOGITS
     buku
    0.50
    しみ
    0.50
    comparing
    0.47
    чить
    0.46
    𝔞
    0.46
     срав
    0.46
    تاب
    0.45
    тивным
    0.45
     comparar
    0.45
    тический
    0.45
    Activations Density 0.001%

    No Known Activations