© 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. 15972
    Prev
    Next
    INDEX
    Explanations

    Buy, take, เอาใจ

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

    นำ, เอา, ไป, กลับ, มา, เสนอ

    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
    s
    0.52
    षी
    0.40
     falso
    0.39
     বিপর্যয়
    0.39
     ier
    0.38
     ক্ষুধা
    0.38
     Hier
    0.38
     হয়েছিলেন
    0.37
    skaya
    0.36
    azgo
    0.36
    POSITIVE LOGITS
     เอา
    0.41
    ].
    0.39
     המס
    0.38
    циона
    0.37
    ที
    0.37
     ký
    0.37
    लिंग
    0.37
    ส่วน
    0.37
    рья
    0.37
    ။
    0.36
    Activations Density 0.000%

    No Known Activations