© 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. 192198
    Prev
    Next
    INDEX
    Explanations

    collaboration and gifts

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

    spilling forth

    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
     ခ
    0.52
    gers
    0.50
     ସ
    0.48
    dst
    0.48
     engines
    0.47
    plätze
    0.47
     ist
    0.46
     ওয়েব
    0.46
    claves
    0.46
    press
    0.46
    POSITIVE LOGITS
    遊び
    0.52
    گاهی
    0.52
    ه‌ای
    0.51
    脣
    0.51
    שי
    0.51
    唇
    0.50
    שית
    0.48
    깥
    0.48
    쏟
    0.47
    ונ
    0.45
    Activations Density 0.001%

    No Known Activations