© 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. 8668
    Prev
    Next
    INDEX
    Explanations

    Battery and batch usage

    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
    𝗹
    3.46
    ל
    3.37
    ان
    3.29
    ן
    3.21
    𝗲
    3.19
    𝗱
    3.19
    𝗿
    3.15
     scintillation
    3.15
    in
    3.12
    ли
    3.11
    POSITIVE LOGITS
    𝘶
    2.85
    impanan
    2.78
    इस
    2.72
    jne
    2.69
     cuales
    2.67
     лица
    2.65
     preved
    2.65
    ۟
    2.62
     widz
    2.61
    ∴
    2.60
    Activations Density 0.160%

    No Known Activations