© 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. 21573
    Prev
    Next
    INDEX
    Explanations

    language context

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

    project request understand

    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
    ্্র
    0.32
    被称为
    0.31
    
    0.30
     λεπ
    0.30
    ঠোর
    0.28
    ্ি
    0.28
    㫣
    0.28
    হইতে
    0.27
    ঞ্চিত
    0.27
    TextBox
    0.27
    POSITIVE LOGITS
     (
    0.41
     fazia
    0.40
     supaya
    0.38
     faça
    0.38
     mais
    0.38
     Saúde
    0.38
     estaban
    0.37
     banal
    0.37
     foram
    0.36
     dieron
    0.36
    Activations Density 0.035%

    No Known Activations