© 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. 29-GEMMASCOPE-2-RES-16K
    7. 3273
    Prev
    Next
    INDEX
    Explanations

    analysts' consensus

    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_29_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
    …,
    1.19
    ,…
    1.15
    )…
    1.12
    .…
    1.09
     …
    1.05
    …)
    1.00
    …).
    0.97
    …
    0.97
     ・
    0.96
    …"
    0.96
    POSITIVE LOGITS
    3.78
    3.37
    2.98
    2.70
    2.52
    2.48
    2.34
    2.12
    2.10
    2.03
    Activations Density 0.342%

    No Known Activations