© 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. 40-GEMMASCOPE-2-RES-65K
    7. 951
    Prev
    Next
    INDEX
    Explanations

    A is followed by descriptive words

    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_40_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
     الوح
    0.47
     Боли
    0.43
     רא
    0.42
    }}+
    0.42
     હતો
    0.41
     وي
    0.40
     Ис
    0.40
    칩
    0.40
    وي
    0.40
    торой
    0.39
    POSITIVE LOGITS
    (
    0.53
     SD
    0.49
     spacing
    0.45
    atin
    0.44
     broadening
    0.44
      
    0.44
     inflamm
    0.44
     anten
    0.44
     biom
    0.44
     behavioral
    0.44
    Activations Density 0.004%

    No Known Activations