© 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. 181549
    Prev
    Next
    INDEX
    Explanations

    prior to

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

    action words

    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
     desses
    0.46
    qld
    0.46
    xido
    0.44
     Winner
    0.43
     près
    0.41
    ｕ
    0.40
    êu
    0.39
     foglie
    0.39
     winner
    0.39
    的书
    0.39
    POSITIVE LOGITS
    诀
    0.39
    buy
    0.38
    运营
    0.38
    რე
    0.38
    Portugal
    0.37
    kinen
    0.37
     perm
    0.37
    Merc
    0.36
     universe
    0.36
    ERT
    0.36
    Activations Density 0.006%

    No Known Activations