© 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. 9-GEMMASCOPE-2-RES-16K
    7. 225
    Prev
    Next
    INDEX
    Explanations

    software distributions

    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_9_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
     اولیه
    1.05
     privileges
    0.98
    ounds
    0.98
    د
    0.97
     reasoning
    0.94
    alade
    0.94
    elves
    0.93
     catheter
    0.89
    doubt
    0.89
     packets
    0.89
    POSITIVE LOGITS
    of
    0.84
    𝗥
    0.72
    وذ
    0.69
    to
    0.69
    كم
    0.69
    tt
    0.68
     आव्हान
    0.67
    ته
    0.67
    жды
    0.67
     AIP
    0.66
    Activations Density 1.162%

    No Known Activations