© 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. 2834
    Prev
    Next
    INDEX
    Explanations

    robust

    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
     vare
    1.68
    ruar
    1.63
    <unused734>
    1.63
     fehlen
    1.60
    壹章
    1.57
    嫋
    1.57
    %).
    1.56
    prese
    1.55
    ProguardFile
    1.54
    どんど
    1.54
    POSITIVE LOGITS
    ↵↵
    1.34
     cataract
    1.16
    ↵↵↵
    1.07
     took
    1.07
     Then
    1.05
     dysplasia
    1.05
     sentenced
    1.03
    LaTeX
    1.02
     cartoonist
    1.02
     vaccin
    1.02
    Activations Density 0.000%

    No Known Activations