© 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. 32410
    Prev
    Next
    INDEX
    Explanations

    our new

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

    alternatives consequence troubleshooting

    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
    2
    0.49
    ಾನ
    0.45
    text
    0.43
    political
    0.43
     Dost
    0.42
    ั
    0.42
    CHARACTER
    0.42
    ן
    0.42
     political
    0.41
     fascinating
    0.41
    POSITIVE LOGITS
     গুঁ
    0.54
     cuisson
    0.50
    髖
    0.50
    ંત્રણ
    0.50
     hátsó
    0.50
     latéraux
    0.47
     কানা
    0.47
     দুধ
    0.47
     نبدا
    0.46
     millimeters
    0.46
    Activations Density 0.000%

    No Known Activations