© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 15685
    Prev
    Next
    INDEX
    Explanations

    bones undergoing transformation

    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_17_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
    handled
    1.15
     suspected
    1.10
     sufficiently
    1.10
    僚
    1.07
    tagged
    1.05
    வரது
    1.04
    नात्मक
    1.04
    htmlspecialchars
    1.04
     unsafe
    1.01
     sister
    0.99
    POSITIVE LOGITS
    ہ
    1.28
     solubilities
    1.25
    ли
    1.20
    ур
    1.09
     concernant
    1.09
     costituito
    1.06
     cancellation
    1.06
     furent
    1.02
     avem
    1.01
     뜨
    1.00
    Activations Density 0.003%

    No Known Activations