© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2195
    Prev
    Next
    INDEX
    Explanations

    elaborate on specific aspects

    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
     adorable
    1.49
     باید
    1.48
     lindos
    1.39
    不仅
    1.36
     Trong
    1.36
     અને
    1.34
     乳
    1.32
     keine
    1.32
    不僅
    1.32
     וש
    1.31
    POSITIVE LOGITS
    topic
    1.12
     topics
    1.06
    Topic
    1.06
     topic
    1.05
    related
    1.01
    Topics
    0.98
    א
    0.94
    topics
    0.93
     Topic
    0.89
    ?)
    0.89
    Activations Density 0.677%

    No Known Activations