© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 218711
    Prev
    Next
    INDEX
    Explanations

    actions and requirements

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

    unlikely, not works

    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
     downregulation
    0.47
    รายการ
    0.45
     싶
    0.43
    菪
    0.43
     다운
    0.43
     cream
    0.42
    erapia
    0.41
    לות
    0.41
     채팅
    0.41
    اند
    0.41
    POSITIVE LOGITS
    married
    0.47
    ᡧ
    0.46
    national
    0.45
    recognized
    0.45
     Европе
    0.44
    𝐬
    0.43
    మన
    0.42
    handled
    0.42
    fellow
    0.42
    aldo
    0.41
    Activations Density 0.002%

    No Known Activations