© 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. 198420
    Prev
    Next
    INDEX
    Explanations

    looks like, prior to, Alexander, signature, works

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

    AI capability

    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
     oplossing
    0.54
     penalties
    0.50
    ці
    0.50
     j
    0.49
     delimiters
    0.47
    anut
    0.46
     instabilities
    0.46
    ophones
    0.46
    et
    0.44
     @
    0.44
    POSITIVE LOGITS
    可能です
    0.48
    好評
    0.46
     કરવાની
    0.45
    ্তিক
    0.45
    日まで
    0.44
    ণিজ্য
    0.44
     देशों
    0.44
     геро
    0.43
    謀
    0.43
     સારી
    0.42
    Activations Density 0.000%

    No Known Activations