© 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. 40-GEMMASCOPE-2-RES-262K
    7. 110684
    Prev
    Next
    INDEX
    Explanations

    longest documented

    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_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
     Susanne
    0.44
    Насе
    0.43
    trop
    0.42
    賠
    0.41
     напи
    0.40
     Battista
    0.40
     buoyancy
    0.39
     physicists
    0.39
    渉
    0.38
     प्रारूप
    0.38
    POSITIVE LOGITS
    把握
    0.38
     fondamentali
    0.37
     embodying
    0.36
     भरोसे
    0.36
     ponctués
    0.35
     hilfre
    0.35
     fondamentale
    0.35
     prioritizing
    0.35
    Fundamental
    0.35
     iguais
    0.34
    Activations Density 0.001%

    No Known Activations