Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 5996
    Prev
    Next
    INDEX
    Explanations

    sensory descriptions

    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
    са
    0.36
    ор
    0.36
     secara
    0.34
    ма
    0.34
    би
    0.33
    ́
    0.33
     sebagai
    0.33
    ungan
    0.33
     शे
    0.32
     другой
    0.32
    POSITIVE LOGITS
     Understand
    0.44
     Decide
    0.41
     maximize
    0.38
     understand
    0.37
     visualize
    0.36
    <0x80>
    0.36
     stressors
    0.36
     maximizing
    0.35
     Firstly
    0.34
     Visualize
    0.34
    Activations Density 3.454%

    No Known Activations