Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 41020
    Prev
    Next
    INDEX
    Explanations

    elements of composition

    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_29_width_65k_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
    𝕖
    1.36
    Eloquent
    1.31
    𝙚
    1.28
    𝙨
    1.26
    على
    1.15
     filepath
    1.14
    𝙃
    1.13
    帼
    1.11
     вариантов
    1.10
    $>$
    1.05
    POSITIVE LOGITS
     constitut
    1.71
     управления
    1.59
     preuve
    1.36
    äv
    1.35
     człon
    1.35
    jén
    1.25
    Xpaths
    1.21
     décl
    1.20
     керу
    1.20
     juicio
    1.18
    Activations Density 0.037%

    No Known Activations