© 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. 30798
    Prev
    Next
    INDEX
    Explanations

    entry was posted

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

    entry point, entry level, entry/exit

    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
    ু
    0.85
    ک
    0.84
    ק
    0.81
    ט
    0.78
    ك
    0.73
    ב
    0.73
    িগ
    0.72
    ח
    0.72
    א
    0.72
    ע
    0.70
    POSITIVE LOGITS
     entrada
    1.37
     entry
    1.30
     Entry
    1.23
     вход
    1.20
     entrance
    1.16
     प्रवेश
    1.16
     entrants
    1.16
     دخول
    1.15
    入
    1.15
    entry
    1.13
    Activations Density 0.065%

    No Known Activations