© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13604
    Prev
    Next
    INDEX
    Explanations

    rhyme scheme

    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
     bacteria
    0.92
    endocrine
    0.89
     ospiti
    0.88
     النوم
    0.86
    bacteria
    0.85
     infections
    0.84
    泌
    0.84
    多い
    0.84
     ovat
    0.83
     Infections
    0.82
    POSITIVE LOGITS
    柞
    0.79
    rentices
    0.78
    ્રા
    0.74
    лоти
    0.73
    ಕ
    0.72
    燾
    0.71
    ㄵ
    0.69
    тового
    0.69
    毌
    0.68
     traversing
    0.68
    Activations Density 0.005%

    No Known Activations