© 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. 16-GEMMASCOPE-2-RES-262K
    7. 48351
    Prev
    Next
    INDEX
    Explanations

    comprehend complex ideas and questions

    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_16_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
    a
    1.66
    া
    1.34
    ا
    1.21
    ه
    1.21
    τ
    1.16
    σε
    1.12
    اک
    1.11
    ा
    1.08
     are
    1.05
    ма
    1.05
    POSITIVE LOGITS
    2
    1.34
     comprehend
    1.27
    5
    1.08
     lauf
    1.03
    ب
    1.01
    3
    0.98
     তারপর
    0.96
     schrift
    0.95
     chegar
    0.93
     comprend
    0.92
    Activations Density 0.005%

    No Known Activations