© 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. 189861
    Prev
    Next
    INDEX
    Explanations

    offering courses and gold

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

    descriptive phrases, comparisons, or actions

    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
     Aquí
    0.46
    Aquí
    0.43
    エル
    0.41
    وأضاف
    0.39
     enfoque
    0.38
    ̆
    0.38
     正規品
    0.38
     거예요
    0.38
     endif
    0.38
     creatives
    0.38
    POSITIVE LOGITS
     carre
    0.41
    ಭಾ
    0.41
    የ
    0.39
     cuales
    0.39
    代理
    0.39
    ನಾಟಕ
    0.38
    MGMT
    0.38
     जर
    0.38
    以上的
    0.37
    ക്കേ
    0.37
    Activations Density 0.001%

    No Known Activations