© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 12513
    Prev
    Next
    INDEX
    Explanations

    tasked with, impact of

    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_22_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
     distinct
    0.83
     исключительно
    0.83
     właśnie
    0.81
     konkrét
    0.80
     unwavering
    0.80
    瞧
    0.79
     تلك
    0.79
     appunto
    0.79
     ấy
    0.78
     entirety
    0.77
    POSITIVE LOGITS
    㳻
    1.05
    <unused2168>
    1.00
    粖
    0.99
    萑
    0.98
    死去
    0.92
    稒
    0.91
    <unused2172>
    0.91
    㕩
    0.91
    晠
    0.89
    <unused2110>
    0.88
    Activations Density 0.341%

    No Known Activations