© 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. 90311
    Prev
    Next
    INDEX
    Explanations

    multiple data modalities

    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
    up
    1.00
    2
    0.94
    ه
    0.93
    ți
    0.85
    illä
    0.79
    ה
    0.78
    uring
    0.77
    시
    0.76
    ्य
    0.76
    사
    0.74
    POSITIVE LOGITS
     modality
    1.11
    م
    1.10
    t
    1.07
    ר
    1.02
    m
    1.02
    র
    1.01
    A
    1.00
    ิ
    0.99
    ب
    0.98
     modalities
    0.95
    Activations Density 0.002%

    No Known Activations