© 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. 224041
    Prev
    Next
    INDEX
    Explanations

    Games Room

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

    contrast options, continuation, consequence, limitation

    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
     dioses
    0.48
     destro
    0.47
     ira
    0.46
    )}}
    0.46
     jungles
    0.45
    خب
    0.44
     يكن
    0.44
     Adrienne
    0.43
    жения
    0.43
     Tutorials
    0.43
    POSITIVE LOGITS
    soph
    0.45
    Radi
    0.43
    闱
    0.43
    s
    0.43
    ς
    0.43
    ሦ
    0.43
    ש
    0.42
    σε
    0.42
    ೃತ
    0.42
    revenue
    0.42
    Activations Density 0.001%

    No Known Activations