© 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. 1706
    Prev
    Next
    INDEX
    Explanations

    Revelation references

    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
    м
    2.34
    ার
    2.05
    ة
    2.00
    ০
    1.90
    en
    1.77
    a
    1.73
    er
    1.70
    an
    1.67
    uole
    1.66
    u
    1.64
    POSITIVE LOGITS
     etapas
    1.30
    Од
    1.28
     procé
    1.27
    براین
    1.21
     त्यामुळे
    1.20
     few
    1.18
    OBER
    1.16
     aucun
    1.15
    あたり
    1.15
     astute
    1.15
    Activations Density 1.780%

    No Known Activations