© 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. 17-GEMMASCOPE-2-RES-16K
    4. 8635
    Prev
    Next
    INDEX
    Explanations

    checking status

    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
     Miscellaneous
    0.94
     العديد
    0.93
    ర్స్
    0.93
     মানসিক
    0.92
    㽚
    0.91
     మరియు
    0.91
    smallestBlock
    0.90
    <unused687>
    0.89
     eLearning
    0.88
    𝘼
    0.87
    POSITIVE LOGITS
     reckoned
    1.17
     reckons
    1.15
     जरिये
    1.10
     tranche
    1.06
     bespoke
    1.06
     paltry
    1.01
     मसलन
    1.01
     hitherto
    1.00
     eponymous
    1.00
     plough
    0.99
    Activations Density 0.029%

    No Known Activations