© 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. 2060
    Prev
    Next
    INDEX
    Explanations

    writing and creating code

    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
    ኅ
    0.37
    Ан
    0.35
     совета
    0.34
     говорят
    0.34
    Arguments
    0.33
    🆚
    0.33
     fieldContext
    0.32
    ಎ
    0.32
    тым
    0.32
    носи
    0.32
    POSITIVE LOGITS
     skapa
    0.50
     crée
    0.49
     piloto
    0.48
     creare
    0.46
     créer
    0.45
     criando
    0.44
     proyecto
    0.44
    yecto
    0.43
    वर
    0.43
     creando
    0.43
    Activations Density 0.538%

    No Known Activations