© 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. 206591
    Prev
    Next
    INDEX
    Explanations

    people speaking to us

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

    specific domains and instructions

    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
     प्रदर्श
    0.53
     पोखर
    0.50
     Kxc
    0.50
     অজ
    0.48
     ध्वनि
    0.47
     ।
    0.47
     ആണ
    0.47
    hamton
    0.46
    atore
    0.46
     冖
    0.46
    POSITIVE LOGITS
    enter
    0.45
     Comando
    0.45
     mov
    0.45
     marshal
    0.44
    ষ্ণ
    0.43
    ens
    0.43
     personal
    0.43
     childhood
    0.43
     following
    0.43
    快捷
    0.43
    Activations Density 0.000%

    No Known Activations