© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7508
    Prev
    Next
    INDEX
    Explanations

    time 'at' followed by number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_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
    昼
    0.57
    の日
    0.56
    universal
    0.56
     daytime
    0.55
    beqz
    0.55
    morning
    0.54
    Rah
    0.53
    inverse
    0.52
    initialized
    0.52
    朝
    0.52
    POSITIVE LOGITS
     Grundlagen
    0.64
     Reserves
    0.61
     Guidelines
    0.59
     begeistert
    0.59
     Interests
    0.57
     Bürger
    0.56
     "):
    0.56
     Lebens
    0.55
     GUID
    0.55
     Farbe
    0.55
    Activations Density 0.122%

    No Known Activations