© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 8031
    Prev
    Next
    INDEX
    Explanations

    injecting or inserting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
    പേ
    0.75
     złoż
    0.68
    揃
    0.65
    वान
    0.64
    চন
    0.64
    ធ
    0.63
     நீதி
    0.62
     dö
    0.62
    盆
    0.62
    utzt
    0.62
    POSITIVE LOGITS
     retrofit
    1.18
     intercept
    1.14
     insertion
    1.07
    insertBefore
    1.06
    Intercept
    1.03
     hijacking
    1.01
     Insertion
    1.01
     retroactive
    0.98
     seamless
    0.98
     disruption
    0.97
    Activations Density 0.432%

    No Known Activations