© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 2818
    Prev
    Next
    INDEX
    Explanations

    left side of body

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ק
    1.25
     Others
    1.02
    م
    0.98
     A
    0.98
     Many
    0.96
     Phones
    0.95
     Stack
    0.94
     Spark
    0.94
     Other
    0.93
     Sections
    0.92
    POSITIVE LOGITS
    ের
    1.24
     derecha
    1.05
     deshalb
    1.02
    izin
    0.95
    Más
    0.94
     griega
    0.93
    Լ
    0.93
     están
    0.93
     izquierda
    0.93
    ciencia
    0.93
    Activations Density 0.003%

    No Known Activations