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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 106
    Prev
    Next
    INDEX
    Explanations

    signal analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     chronology
    2.95
     wherever
    2.92
     festivities
    2.79
    囝
    2.73
     announcements
    2.71
     arrows
    2.71
    dated
    2.70
    Organisation
    2.70
     adjournment
    2.65
     historians
    2.64
    POSITIVE LOGITS
    7
    2.55
    6
    2.35
    8
    2.28
    4
    2.21
    3
    2.19
    5
    1.97
     demanda
    1.87
     exista
    1.87
    9
    1.82
    ستخدم
    1.79
    Activations Density 0.593%

    No Known Activations