© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 9006
    Prev
    Next
    INDEX
    Explanations

    summarizing phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_262k_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
    N
    0.65
     例えば
    0.64
    L
    0.62
    например
    0.61
    Л
    0.61
    J
    0.59
    例えば
    0.59
    リ
    0.57
    U
    0.55
    ل
    0.55
    POSITIVE LOGITS
     multifaceted
    0.74
     vielfält
    0.65
     safegu
    0.64
     faciliter
    0.64
     bestowed
    0.63
     samt
    0.62
     aufgrund
    0.60
     whose
    0.60
     safeguarding
    0.59
     memenuhi
    0.59
    Activations Density 0.001%

    No Known Activations