© 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. 47392
    Prev
    Next
    INDEX
    Explanations

    fitness, job, research, ideas

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

    promise, protected, start, feared, driving, run, intended

    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
    enty
    0.52
    quoise
    0.50
    ئة
    0.50
    ﺔ
    0.49
    échange
    0.49
    ní
    0.48
    omin
    0.48
    時候
    0.48
    asure
    0.47
    ا
    0.47
    POSITIVE LOGITS
     mette
    0.44
     meningkatkan
    0.44
    提升
    0.44
     প্রশিক্ষ
    0.43
     ब्रे
    0.43
     biodegrad
    0.43
    >>&
    0.42
     Qo
    0.42
     graduating
    0.42
     rounds
    0.41
    Activations Density 0.000%

    No Known Activations