© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 111181
    Prev
    Next
    INDEX
    Explanations

    intelligence differences

    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
    VM
    0.51
    alski
    0.49
     ermög
    0.48
     xuân
    0.46
     Fellow
    0.46
    йде
    0.45
     Nairobi
    0.45
    
    0.44
    `)
    0.44
     साम्रा
    0.43
    POSITIVE LOGITS
    тические
    0.49
     wiel
    0.46
     بينا
    0.46
     situación
    0.45
     instalación
    0.45
    ablemente
    0.45
    ري
    0.45
    Bigg
    0.45
    傩
    0.44
    fection
    0.43
    Activations Density 0.002%

    No Known Activations