© 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. 16275
    Prev
    Next
    INDEX
    Explanations

    negative contractions

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

    advice and instructions

    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
     يُ
    0.70
    💞
    0.63
     нередко
    0.62
    めっちゃ
    0.61
     👇
    0.59
    💟
    0.59
     تُ
    0.57
     médias
    0.57
     galore
    0.56
    ❣️
    0.56
    POSITIVE LOGITS
     ব্যাবস্থা
    0.64
     까지
    0.63
     busses
    0.61
     Russel
    0.61
     ব্যপারে
    0.60
     E
    0.58
     recieved
    0.57
     McDonalds
    0.57
     उन्ह
    0.57
     Wright
    0.56
    Activations Density 0.250%

    No Known Activations