© 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. 54649
    Prev
    Next
    INDEX
    Explanations

    weekly report format

    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
     🤗
    0.45
    ит
    0.44
    лет
    0.43
    ги
    0.42
    ография
    0.42
     néanmoins
    0.42
     нам
    0.42
     дода
    0.42
    🤗
    0.42
    лен
    0.41
    POSITIVE LOGITS
     Protestants
    0.43
    SON
    0.42
    šu
    0.38
     Özel
    0.37
    whose
    0.37
    ming
    0.36
     blieb
    0.36
    FORM
    0.36
    状况
    0.36
    indsay
    0.36
    Activations Density 0.013%

    No Known Activations