© 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-16K
    7. 9660
    Prev
    Next
    INDEX
    Explanations

    specification, quantity, example

    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_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
    ,’’
    0.44
    íu
    0.42
    Misc
    0.41
    Ди
    0.40
     приорите
    0.39
    ୌ
    0.38
     дета
    0.37
    Ана
    0.37
    Though
    0.37
     нега
    0.36
    POSITIVE LOGITS
    Დ
    0.64
    Ს
    0.62
    Რ
    0.61
    Ა
    0.58
     అతను
    0.56
    Გ
    0.55
     ක්ර
    0.55
     XNUMX
    0.53
    Პ
    0.51
    Მ
    0.50
    Activations Density 0.045%

    No Known Activations