© 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. 97532
    Prev
    Next
    INDEX
    Explanations

    best results, followed by

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

    Avoiding Predators

    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
    üm
    0.48
     हिस्सा
    0.46
     少
    0.46
     सगळ्या
    0.46
    ế
    0.45
     cinética
    0.44
    桶
    0.44
    召
    0.44
     叶
    0.43
    ору
    0.43
    POSITIVE LOGITS
    workouts
    0.49
     workouts
    0.47
     Jut
    0.44
     rebound
    0.43
    ওয়ায়
    0.42
     Chel
    0.42
     defenses
    0.42
     Ultra
    0.42
     unforeseen
    0.41
     nothing
    0.40
    Activations Density 0.000%

    No Known Activations