© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 2521
    Prev
    Next
    INDEX
    Explanations

    systems and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
    তিক্রম
    0.79
     cascading
    0.69
    ched
    0.68
     알
    0.67
     salicylic
    0.64
     simple
    0.64
     치
    0.64
    achi
    0.64
     cascade
    0.63
    ис
    0.63
    POSITIVE LOGITS
     savent
    0.89
     proposer
    0.81
    _(
    0.79
    PagerAdapter
    0.78
     повинні
    0.78
    argv
    0.78
    arrive
    0.75
    Deployment
    0.74
    Opportun
    0.74
     know
    0.74
    Activations Density 0.496%

    No Known Activations