© 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. 135637
    Prev
    Next
    INDEX
    Explanations

    company names

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

    venom and toxins

    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
    牆
    0.44
     Takashi
    0.41
    وجود
    0.41
    jeu
    0.41
    ór
    0.40
    啓
    0.40
     holo
    0.38
     Trigger
    0.38
    ্যন্ত
    0.38
    ニチ
    0.38
    POSITIVE LOGITS
     ceremon
    0.44
     посте
    0.42
     tổn
    0.42
    ustomed
    0.42
    че
    0.42
     зарубе
    0.42
     тамо
    0.41
    дем
    0.41
    粼
    0.40
    绵
    0.40
    Activations Density 0.015%

    No Known Activations