© 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-262K
    7. 9382
    Prev
    Next
    INDEX
    Explanations

    national-helpline

    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_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
     enchanting
    0.94
     portug
    0.93
     pretentious
    0.87
     Honestly
    0.87
     Είναι
    0.86
    ς
    0.86
     annum
    0.84
     girly
    0.84
     Accountants
    0.83
     ophthal
    0.83
    POSITIVE LOGITS
    𝐼
    0.91
    e
    0.88
    tura
    0.87
    QueryResult
    0.85
    𝐿
    0.85
    વાના
    0.82
    𝑙
    0.82
    HashMap
    0.81
    triggered
    0.80
    ҳои
    0.80
    Activations Density 0.078%

    No Known Activations