© 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. 9038
    Prev
    Next
    INDEX
    Explanations

    SaaS application, gone wrong, Cobalt Soul

    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
    ল
    4.32
    𝘢
    4.00
    𝘳
    3.84
    ल
    3.71
    y
    3.65
    𝘪
    3.64
    𝘰
    3.47
    𝘭
    3.40
    r
    3.38
    o
    3.33
    POSITIVE LOGITS
    ような
    3.02
    которые
    2.88
     fortunes
    2.84
    कर्ताओं
    2.68
    !--
    2.65
    깐
    2.62
    要
    2.56
    смотря
    2.48
     Arx
    2.46
    ہیں
    2.46
    Activations Density 0.092%

    No Known Activations