© 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. 143503
    Prev
    Next
    INDEX
    Explanations

    confirmed survivors

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

    confirmation or ending

    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
     Puoi
    0.49
     dapat
    0.48
     artı
    0.47
     tertentu
    0.47
    可以在
    0.46
     ему
    0.45
     /ˈ
    0.44
    ERCE
    0.43
     itin
    0.43
     আর্ত
    0.43
    POSITIVE LOGITS
    Confirm
    0.43
    irect
    0.43
    बाबत
    0.41
    瑞
    0.41
    Ach
    0.41
     Sta
    0.41
    Survivor
    0.40
     Survivors
    0.40
    confirmed
    0.40
    Sta
    0.40
    Activations Density 0.000%

    No Known Activations