© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 148329
    Prev
    Next
    INDEX
    Explanations

    document.getElementById calls

    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_29_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
    ഞ്ചി
    0.67
    Relationships
    0.66
    «
    0.66
    ')+
    0.66
     নায়
    0.65
    }}$-
    0.64
    続く
    0.63
    为此
    0.63
    ĕç
    0.63
    নেই
    0.62
    POSITIVE LOGITS
     REI
    0.82
     Emmett
    0.74
     ECC
    0.71
     CLEAN
    0.71
     Oakland
    0.71
    的高度
    0.71
     scrolling
    0.70
     LEARN
    0.70
     Rhin
    0.70
     ROD
    0.70
    Activations Density 0.011%

    No Known Activations