© 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-16K
    7. 4525
    Prev
    Next
    INDEX
    Explanations

    capable of

    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
     અને
    1.06
     आणि
    1.05
     ਅਤੇ
    1.04
     और
    1.01
     এবং
    1.01
     và
    1.00
     και
    1.00
     и
    0.94
    และ
    0.93
     ಮತ್ತು
    0.88
    POSITIVE LOGITS
     zugleich
    0.43
     whatnot
    0.42
     viens
    0.39
    katapos
    0.39
    ipherals
    0.38
    නි
    0.38
     somit
    0.37
     duniya
    0.37
     plays
    0.37
     hanging
    0.36
    Activations Density 0.529%

    No Known Activations