© 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. 8663
    Prev
    Next
    INDEX
    Explanations

    prompts

    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
    াড়া
    0.46
    я
    0.45
    y
    0.44
    кому
    0.43
    IDER
    0.43
    шина
    0.42
    itale
    0.41
    URY
    0.39
    η
    0.39
    ੱਚ
    0.39
    POSITIVE LOGITS
     регионе
    0.46
    0.45
     críticas
    0.44
     spéciaux
    0.44
     premiers
    0.43
     práticas
    0.43
     magní
    0.42
    ulares
    0.42
     frío
    0.42
     Lij
    0.41
    Activations Density 0.167%

    No Known Activations