© 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. 20014
    Prev
    Next
    INDEX
    Explanations

    template text examples

    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
     pay
    0.42
     দেবতাদের
    0.42
     aby
    0.41
     grads
    0.40
     do
    0.40
     日
    0.39
     payday
    0.39
    дь
    0.38
     pathogens
    0.38
     yap
    0.38
    POSITIVE LOGITS
     iniziamo
    0.39
     రెండు
    0.38
    小学校
    0.38
    +}\
    0.37
    ುದ
    0.37
    зне
    0.37
    úblic
    0.37
    ioso
    0.36
    .}\
    0.35
    }(\
    0.35
    Activations Density 0.096%

    No Known Activations