© 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. 227630
    Prev
    Next
    INDEX
    Explanations

    tradition

    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
    㕵
    0.44
    奪
    0.43
    Determination
    0.43
     Doğ
    0.43
    業
    0.43
     требо
    0.42
     تغيير
    0.41
     प्लानिंग
    0.41
     سيكون
    0.41
     ሊ
    0.41
    POSITIVE LOGITS
     breached
    0.53
     INTERNAL
    0.53
     hydrolyzed
    0.52
     pretzels
    0.49
     towels
    0.48
    ЕВ
    0.46
     superseded
    0.46
     sows
    0.46
     fingerprints
    0.45
     surpassed
    0.45
    Activations Density 0.000%

    No Known Activations