© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 693
    Prev
    Next
    INDEX
    Explanations

    two times doubling

    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
    altered
    0.96
    -
    0.94
     abbia
    0.94
    rified
    0.93
    annya
    0.93
    atively
    0.90
    -/
    0.90
    glazed
    0.89
    /
    0.89
    lessness
    0.88
    POSITIVE LOGITS
    この
    1.36
     इस
    1.36
     اگر
    1.27
     Interestingly
    1.26
     This
    1.24
     Despite
    1.23
     если
    1.23
     この
    1.23
     Ayrıca
    1.22
     However
    1.20
    Activations Density 0.813%

    No Known Activations