© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 145571
    Prev
    Next
    INDEX
    Explanations

    chemical naming, association, verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    رت
    0.55
     পদ্ধ
    0.52
     testaceis
    0.52
    ्यास
    0.51
    یه
    0.51
     Gonzalez
    0.50
     Colleen
    0.50
     errore
    0.50
    𐱅
    0.50
    𝟬
    0.50
    POSITIVE LOGITS
    <0xE3>
    0.47
    Silence
    0.42
    Listening
    0.41
    jaw
    0.40
    înes
    0.40
     bubbling
    0.39
    down
    0.38
    柄
    0.38
    Killing
    0.38
    pressure
    0.37
    Activations Density 0.000%

    No Known Activations