© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 1207
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     recal
    0.42
     num
    0.40
     メ
    0.39
     proc
    0.38
     mrt
    0.37
     bh
    0.36
    จากการ
    0.36
    지
    0.36
     sz
    0.36
    กระจ
    0.36
    POSITIVE LOGITS
    ónicas
    0.60
    émico
    0.57
    émica
    0.56
    áře
    0.54
    ámica
    0.53
    alámb
    0.50
    čné
    0.50
    otipos
    0.49
    ónico
    0.48
    ossal
    0.48
    Activations Density 0.608%

    No Known Activations