© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 54042
    Prev
    Next
    INDEX
    Explanations

    invoice or list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ballast
    0.43
    II
    0.40
     more
    0.40
    YR
    0.40
    áll
    0.39
     I
    0.39
    то
    0.39
    巷
    0.39
    она
    0.39
    ストレス
    0.39
    POSITIVE LOGITS
     darunter
    0.48
    ہد
    0.47
     اوپر
    0.46
     Geschenk
    0.45
     lediglich
    0.44
     ہدایت
    0.43
     사용하여
    0.42
     daz
    0.42
     Utilisez
    0.42
     wobei
    0.42
    Activations Density 0.010%

    No Known Activations