© 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. 54534
    Prev
    Next
    INDEX
    Explanations

    expresses dependency or conditionality

    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
     which
    0.40
    which
    0.38
    Define
    0.38
    𝘦
    0.38
     предупре
    0.38
    脸
    0.38
     გან
    0.37
    ától
    0.37
    erné
    0.37
    inction
    0.37
    POSITIVE LOGITS
     cookbooks
    0.46
     humains
    0.45
     třeba
    0.44
     dieting
    0.43
    <unused3>
    0.41
     некоторое
    0.40
     cookware
    0.40
     मुकद
    0.39
     বই
    0.39
    న్య
    0.39
    Activations Density 0.001%

    No Known Activations