© 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. 28239
    Prev
    Next
    INDEX
    Explanations

    journalism and financial terms

    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
    ம
    0.40
    வியில்
    0.39
     texId
    0.38
    த்தனை
    0.37
     durchaus
    0.37
     alloys
    0.37
     juguetes
    0.36
     বিশেষ
    0.35
     선택
    0.35
     designs
    0.35
    POSITIVE LOGITS
     journalist
    0.55
     periodista
    0.55
    :
    0.55
     journalism
    0.54
     финансо
    0.54
    📝
    0.53
     journalistic
    0.52
     onboarding
    0.52
     Journalism
    0.51
     escrow
    0.51
    Activations Density 0.026%

    No Known Activations