© 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. 83372
    Prev
    Next
    INDEX
    Explanations

    estate plans, drink, sewer grate, Ice Lemon, smile, weakness

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

    felt natural

    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
     Дон
    0.47
    鎊
    0.47
    ОР
    0.45
     што
    0.44
    어도
    0.42
    ドン
    0.42
    쇤
    0.41
    ал
    0.41
     DWORD
    0.41
    지만
    0.41
    POSITIVE LOGITS
    ณ
    0.50
     biased
    0.50
     साथी
    0.46
     fueled
    0.46
    coupled
    0.46
     ignited
    0.45
     chibi
    0.45
    ுகிறார்கள்
    0.45
    fueled
    0.45
     قیادت
    0.44
    Activations Density 0.002%

    No Known Activations