© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 40686
    Prev
    Next
    INDEX
    Explanations

    depending on what

    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
    导
    0.46
    婫
    0.45
     conç
    0.44
     якія
    0.43
    设备
    0.42
     ktorí
    0.42
    㢦
    0.42
    過程中
    0.41
     alerg
    0.41
    欳
    0.41
    POSITIVE LOGITS
    nent
    0.47
     Soldiers
    0.46
     eponymous
    0.46
    iert
    0.45
    ného
    0.44
    leurs
    0.43
     seer
    0.43
     \{\
    0.42
     for
    0.41
    bruck
    0.41
    Activations Density 0.014%

    No Known Activations