© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5634
    Prev
    Next
    INDEX
    Explanations

    date ranges ending in present

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_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
    ించాలని
    0.71
     jambes
    0.70
    ITHER
    0.66
    ![
    0.66
     totiž
    0.66
     infatti
    0.65
     columnist
    0.65
    !`
    0.65
     namelijk
    0.65
     bowiem
    0.64
    POSITIVE LOGITS
     Present
    1.53
    Present
    1.35
     present
    1.19
    present
    1.18
     présent
    1.17
     presente
    1.14
     PRESENT
    1.08
     Beyond
    0.99
    PRESENT
    0.92
     prezent
    0.90
    Activations Density 0.082%

    No Known Activations