© 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. 32507
    Prev
    Next
    INDEX
    Explanations

    dictionary and quotes

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

    etymological roots

    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
    卡
    0.41
    游客
    0.39
    quí
    0.38
    男友
    0.37
    ড
    0.37
    节点
    0.36
    剧情
    0.36
    ການ
    0.35
     আগামী
    0.35
    体验
    0.35
    POSITIVE LOGITS
     Ceylon
    0.46
     facsimile
    0.45
     occidental
    0.44
     atthakath
    0.43
    ،
    0.42
     quotations
    0.40
     Atkinson
    0.39
     Sinhalese
    0.39
     ...,
    0.38
     oral
    0.38
    Activations Density 0.000%

    No Known Activations