© 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. 9447
    Prev
    Next
    INDEX
    Explanations

    abstract qualities like conciseness

    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
    iénd
    1.68
    座
    1.66
    ی
    1.64
    勮
    1.62
    勬
    1.62
    ി
    1.58
    INCRE
    1.57
    minimize
    1.56
    tom
    1.54
     sendo
    1.53
    POSITIVE LOGITS
    ان
    2.04
    ie
    1.99
    an
    1.97
    <0x80>
    1.96
    е
    1.94
    ant
    1.91
    >>>
    1.87
    પણે
    1.81
    age
    1.80
    kari
    1.79
    Activations Density 0.004%

    No Known Activations