© 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-65K
    7. 2124
    Prev
    Next
    INDEX
    Explanations

    the creation and structure of nodes within a binary tree during key insertion.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    all VRAM, beautiful soul, giant heat

    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
     Zentral
    0.36
     Neue
    0.33
     چ
    0.33
     پلی
    0.32
     Cré
    0.30
    长安
    0.30
    Pol
    0.30
    Ma
    0.30
    چ
    0.30
     Biał
    0.30
    POSITIVE LOGITS
    咶
    0.34
    চ্ছিল
    0.33
    ফতরের
    0.33
    ीण
    0.33
    르는
    0.33
     worldRank
    0.33
    르
    0.33
    streetmap
    0.32
    etição
    0.32
    ając
    0.32
    Activations Density 2.282%

    No Known Activations