© 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. 134943
    Prev
    Next
    INDEX
    Explanations

    money and location

    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
    最強
    0.47
    變化
    0.44
    唷
    0.43
    ch
    0.41
    য়ের
    0.40
    ce
    0.40
    ك
    0.39
    屾
    0.39
    chave
    0.39
    または
    0.38
    POSITIVE LOGITS
     perhitungan
    0.52
    телем
    0.47
     بود
    0.45
     thống
    0.45
     jumped
    0.43
    сию
    0.43
    ЛЬ
    0.43
    फ्तार
    0.43
     مردم
    0.42
    计算
    0.41
    Activations Density 0.003%

    No Known Activations