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. 17-GEMMASCOPE-2-RES-65K
    4. 47344
    Prev
    Next
    INDEX
    Explanations

    "slightly" + "different/complex/daunting"

    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_17_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
    また
    1.07
     threat
    1.00
    送料無料
    0.99
     kubwa
    0.99
    =}
    0.97
    S
    0.95
    drawable
    0.94
     сем
    0.93
     الأمريكية
    0.93
    beta
    0.92
    POSITIVE LOGITS
     energetically
    1.26
    DBES
    1.23
    рни
    1.20
    𝘥
    1.17
    ective
    1.17
    tev
    1.17
    воря
    1.17
     घेऊन
    1.16
    при
    1.13
    jom
    1.12
    Activations Density 0.001%

    No Known Activations