© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 45389
    Prev
    Next
    INDEX
    Explanations

    time periods and progression

    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
     薄
    0.42
    apadam
    0.41
    เตอร์
    0.40
    পাশ
    0.39
     தோன்ற
    0.39
    㯎
    0.38
    抹
    0.38
    )、
    0.37
    quare
    0.37
    
    0.37
    POSITIVE LOGITS
     later
    0.71
     senere
    0.66
     später
    0.56
     później
    0.56
     weeks
    0.56
     weken
    0.56
     senare
    0.56
    Later
    0.55
     semanas
    0.55
     months
    0.53
    Activations Density 0.013%

    No Known Activations