© 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-3-12B-IT
    5. 41-GEMMASCOPE-2-RES-65K
    7. 1774
    Prev
    Next
    INDEX
    Explanations

    description

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_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
    assade
    0.38
    fro
    0.37
     Fmat
    0.37
    aların
    0.36
     至
    0.36
    све
    0.35
    优质
    0.35
    attered
    0.35
    irono
    0.35
    Ľ
    0.35
    POSITIVE LOGITS
    <eos>
    0.47
     doctrine
    0.43
     le
    0.37
     ancestry
    0.36
     WLR
    0.35
     livelihood
    0.35
     essenti
    0.35
    полне
    0.34
     backstory
    0.34
     lifes
    0.34
    Activations Density 0.000%

    No Known Activations