© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 143189
    Prev
    Next
    INDEX
    Explanations

    valuation, average, work, increase, excitement

    np_acts-logits-general · gemini-2.5-flash-lite

    furniture, Italian, score, browse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     기초
    0.55
    เวอร์
    0.55
     двух
    0.52
     środ
    0.51
     联系
    0.50
    damageCount
    0.50
    ຕິດຕໍ່
    0.50
    ᴬ
    0.50
    ທີ່ມີ
    0.49
     கெல்வின்
    0.49
    POSITIVE LOGITS
     congested
    0.46
    .”
    0.46
     congestion
    0.46
     equally
    0.46
     increase
    0.44
     excitement
    0.44
    ,”
    0.44
     accommodate
    0.44
     spilled
    0.43
     escalate
    0.43
    Activations Density 0.001%

    No Known Activations