© 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. 149571
    Prev
    Next
    INDEX
    Explanations

    phrases and common sequences

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

    Japanese family

    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
    Virat
    0.46
    אַ
    0.45
    獒
    0.45
     Казіно
    0.45
     हुन्छ
    0.44
    DataXYZ
    0.43
    Psal
    0.43
    cosity
    0.43
    Ṛ
    0.43
     Begriffe
    0.43
    POSITIVE LOGITS
     componentes
    0.49
     con
    0.46
     прове
    0.46
    水道
    0.46
     mora
    0.45
     vs
    0.44
     cih
    0.43
     capa
    0.43
     frutos
    0.42
     xét
    0.41
    Activations Density 0.001%

    No Known Activations