© 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. 1572
    Prev
    Next
    INDEX
    Explanations

    rainbow colors

    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
    ำ
    0.42
     अवार्ड
    0.42
     Encounter
    0.41
     Qualifying
    0.39
     DATE
    0.39
    を除
    0.38
     Synchronization
    0.38
    ﻨ
    0.37
     Date
    0.37
    enzel
    0.37
    POSITIVE LOGITS
    messageInfo
    0.57
     egip
    0.55
     shrimps
    0.54
     murs
    0.54
    sores
    0.52
     giữa
    0.52
     cumin
    0.51
    cpf
    0.51
     antara
    0.50
     vestib
    0.50
    Activations Density 0.008%

    No Known Activations