© 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. 22-GEMMASCOPE-2-RES-262K
    4. 4729
    Prev
    Next
    INDEX
    Explanations

    explains what subjects say

    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_22_width_262k_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
    Prom
    0.72
     purporting
    0.66
    Styled
    0.63
     ->
    0.62
    Fake
    0.62
     ควร
    0.61
    String
    0.60
    Basic
    0.59
     ciphertext
    0.58
     <-
    0.58
    POSITIVE LOGITS
     explains
    2.83
     explain
    2.40
     explica
    2.32
     explained
    2.32
     spiega
    2.28
     says
    2.25
     explique
    2.20
     menjelaskan
    2.16
     объяс
    2.06
     Explain
    2.04
    Activations Density 0.051%

    No Known Activations