© 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. 686
    Prev
    Next
    INDEX
    Explanations

    nonhuman, non-volatile, Non-Destructive, non-tertiary, Non-Linear, non-judgmental, Non-entity

    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
    น้ำ
    2.51
    ligt
    2.44
    م
    2.40
    ted
    2.36
    mot
    2.34
    self
    2.34
    to
    2.33
    খাস্ত
    2.33
    ত
    2.29
     disparu
    2.28
    POSITIVE LOGITS
    и
    2.53
     totaling
    2.20
    ً
    2.09
    pped
    2.04
    ा
    2.02
     GAAP
    2.00
    GMO
    1.98
    assertArg
    1.95
    -
    1.94
    ്
    1.93
    Activations Density 0.415%

    No Known Activations