© 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
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 201
    Prev
    Next
    INDEX
    Explanations

    K or google

    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
    '
    0.75
    が
    0.73
    は
    0.67
    に
    0.66
    %>%
    0.65
    ي
    0.63
     أنه
    0.63
     смеси
    0.63
     -------------
    0.62
     wander
    0.60
    POSITIVE LOGITS
    ired
    0.62
    %)
    0.62
    ॉफ्ट
    0.59
    ′,
    0.59
    德国
    0.59
    png
    0.59
     proclaimed
    0.58
    国务院
    0.58
     endangered
    0.58
    weds
    0.58
    Activations Density 0.526%

    No Known Activations