© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 17219
    Prev
    Next
    INDEX
    Explanations

    building or simplifying structures

    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
    ید
    0.45
    печа
    0.44
    Ap
    0.43
    larda
    0.42
    잍
    0.42
     océano
    0.41
     alternatively
    0.41
    expédition
    0.40
     aquaculture
    0.40
     tonight
    0.40
    POSITIVE LOGITS
    员
    0.43
    除非
    0.40
     damages
    0.38
    傌
    0.38
    ض
    0.38
    焚
    0.38
    勉
    0.37
     successor
    0.37
    悲
    0.37
     ঐতি
    0.36
    Activations Density 0.001%

    No Known Activations