© 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-262K
    7. 108985
    Prev
    Next
    INDEX
    Explanations

    image generation and translation

    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_262k_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
    탈
    0.44
    رر
    0.43
    *
    0.43
     shrink
    0.42
    निर्देश
    0.42
    導致
    0.42
    屋
    0.41
    ネット
    0.41
    political
    0.41
    ᙱ
    0.41
    POSITIVE LOGITS
     Goethe
    0.59
     peritone
    0.52
     Allemagne
    0.52
     thisStudent
    0.51
    fondo
    0.51
     Ecke
    0.51
     GoObject
    0.50
     elementType
    0.50
     Lenz
    0.50
     ønsker
    0.50
    Activations Density 0.000%

    No Known Activations