© 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. 50148
    Prev
    Next
    INDEX
    Explanations

    chemical formulas and identifiers

    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
    писание
    0.43
     intramuscular
    0.40
    物质
    0.39
     conforms
    0.39
    흘
    0.38
    وية
    0.37
    ఆ
    0.37
     산
    0.36
    Assim
    0.36
    detailID
    0.36
    POSITIVE LOGITS
     Rohingya
    0.38
     Retrieved
    0.37
    enched
    0.37
     Setelah
    0.37
    enda
    0.37
     {}
    0.35
    icletas
    0.35
    °.
    0.35
    oconut
    0.35
     ನಂತರ
    0.35
    Activations Density 0.002%

    No Known Activations