© 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. 109741
    Prev
    Next
    INDEX
    Explanations

    herbal materia and basic concepts

    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
     ≤
    0.46
    ＞
    0.42
     ถูก
    0.41
    []>
    0.40
     કા
    0.40
     กำ
    0.40
    పోయింది
    0.39
     ≥
    0.39
     продаж
    0.39
    ungee
    0.39
    POSITIVE LOGITS
    並
    0.35
    孫
    0.35
    Editable
    0.35
    邑
    0.35
     kenapa
    0.34
     depositing
    0.34
     ንጥረ
    0.34
     vigil
    0.34
    idium
    0.34
     Felic
    0.34
    Activations Density 0.000%

    No Known Activations