© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 35885
    Prev
    Next
    INDEX
    Explanations

    "copy" or "print" documents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ఛ
    0.41
     LANA
    0.38
    阿里云
    0.37
     resid
    0.36
    र्ट
    0.36
     چهار
    0.36
     Resident
    0.36
    anic
    0.36
     Resid
    0.36
    莯
    0.36
    POSITIVE LOGITS
    τίας
    0.40
    faction
    0.37
     جزء
    0.36
     cien
    0.36
     apparence
    0.36
    COPY
    0.36
     copie
    0.35
     capas
    0.35
    OFF
    0.35
     afsl
    0.34
    Activations Density 0.000%

    No Known Activations