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. 9-GEMMASCOPE-2-RES-262K
    4. 7215
    Prev
    Next
    INDEX
    Explanations

    upper bound initialization

    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
    }$\
    2.59
    baiki
    2.35
     Kxg
    2.34
    athione
    2.30
     sake
    2.26
     việc
    2.24
     supernatant
    2.23
     gemacht
    2.22
    ยนต์
    2.20
     uniformity
    2.17
    POSITIVE LOGITS
    ாக
    2.74
     bilj
    2.61
    ių
    2.59
    d
    2.58
    iis
    2.56
    тран
    2.56
    ките
    2.54
    其中
    2.52
    erder
    2.52
    eniz
    2.49
    Activations Density 0.020%

    No Known Activations