© 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
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7084
    Prev
    Next
    INDEX
    Explanations

    avoids recursion and repetition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eminently
    1.53
    Notwithstanding
    1.52
     —
    1.48
     offenbar
    1.45
     erstwhile
    1.44
     nascent
    1.40
     –
    1.37
     esche
    1.34
     हसीना
    1.34
    న్‌
    1.33
    POSITIVE LOGITS
     alot
    1.53
    非常的
    1.44
    很多的
    1.33
     recieve
    1.25
    不断的
    1.24
    됬
    1.19
    썻
    1.13
     recieved
    1.13
     लोगो
    1.11
     consist
    1.11
    Activations Density 0.375%

    No Known Activations