© 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. 74001
    Prev
    Next
    INDEX
    Explanations

    Chaco landscape, fleet, shares, performance

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

    Aretha Franklin, dividend growth, labour market, emotional eating

    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
     No
    0.49
    Type
    0.48
     Some
    0.46
    Pet
    0.46
     Pie
    0.46
     I
    0.46
     Al
    0.46
     Where
    0.46
     Sachin
    0.46
    Pie
    0.45
    POSITIVE LOGITS
     ciała
    0.51
    🦦
    0.47
    chandelier
    0.47
    ίων
    0.47
    cccnc
    0.46
    浮か
    0.46
    ণ্ডল
    0.46
    뗑
    0.46
    売り
    0.45
    돔
    0.45
    Activations Density 0.000%

    No Known Activations