© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 678
    Prev
    Next
    INDEX
    Explanations

    let followed by mathematical symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_16k_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
     canadian
    2.37
     Iranian
    2.21
     scratching
    2.20
     ayurved
    2.18
     Indonesian
    2.18
    
    2.18
     persian
    2.18
     Vedic
    2.18
     occult
    2.16
     spinning
    2.16
    POSITIVE LOGITS
    A
    0.08
     A
    0.06
     P
    0.03
     X
    0.01
     D
    0.01
    P
    0.00
     Z
    -0.03
     E
    -0.04
    D
    -0.04
    C
    -0.05
    Activations Density 0.965%

    No Known Activations