© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2825
    Prev
    Next
    INDEX
    Explanations

    to access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     Mourinho
    1.08
    sses
    0.97
    패
    0.96
     dressed
    0.94
     darken
    0.89
    쌀
    0.86
     wore
    0.85
     remise
    0.85
     WHITE
    0.83
     Candida
    0.82
    POSITIVE LOGITS
    Alma
    1.30
     Aya
    1.23
    Interact
    1.18
     Interact
    1.15
    之心
    1.15
     오픈
    1.14
    詠
    1.14
     Founding
    1.12
    Platforms
    1.10
    autog
    1.09
    Activations Density 0.368%

    No Known Activations