© 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. 59023
    Prev
    Next
    INDEX
    Explanations

    insured up to

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

    line, circles, flexible materials, platforms

    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
    セット
    0.53
    по
    0.53
    지
    0.48
    ст
    0.46
    വ
    0.46
    ポ
    0.46
    Ֆ
    0.46
    ስታ
    0.45
    브
    0.45
    <0xB9>
    0.45
    POSITIVE LOGITS
     dyed
    0.46
     chores
    0.45
     getId
    0.44
     pouquinho
    0.44
     obchod
    0.44
    าค
    0.44
     ধরেই
    0.43
    andt
    0.43
     تمر
    0.43
     علت
    0.42
    Activations Density 0.001%

    No Known Activations