© 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. 13547
    Prev
    Next
    INDEX
    Explanations

    oxygen, count changes

    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
    课题
    0.43
    抬头
    0.42
    团队
    0.41
    谲
    0.39
    드로
    0.38
    ཿ
    0.38
    链路
    0.38
    勹
    0.38
     گزر
    0.38
     ScriptInterface
    0.38
    POSITIVE LOGITS
     hospital
    0.52
     consumer
    0.47
    consumer
    0.45
     playgrounds
    0.44
    Зна
    0.44
    ोर्ट
    0.43
     outlets
    0.43
     gastos
    0.42
     szpital
    0.42
    iness
    0.42
    Activations Density 0.012%

    No Known Activations