© 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. 40-GEMMASCOPE-2-RES-262K
    7. 33036
    Prev
    Next
    INDEX
    Explanations

    identifying states of emptiness

    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_40_width_262k_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
    츤
    0.41
    Fit
    0.38
    ষ্ট
    0.36
    TTL
    0.36
     BRCA
    0.35
    遺伝
    0.35
    igde
    0.35
    Managed
    0.34
    attoos
    0.34
    שור
    0.34
    POSITIVE LOGITS
     empty
    2.97
    empty
    2.72
     Empty
    2.61
    Empty
    2.53
    空
    2.42
     emptiness
    2.36
     EMPTY
    2.28
    空的
    2.19
     empt
    2.13
     kosong
    2.11
    Activations Density 0.031%

    No Known Activations