© 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. 2591
    Prev
    Next
    INDEX
    Explanations

    critical ethical considerations

    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
    rinsic
    1.00
    6
    0.97
     Karna
    0.89
    ﺖ
    0.88
    5
    0.88
     recoil
    0.88
    7
    0.86
    凧
    0.85
    freie
    0.83
     mesenchymal
    0.83
    POSITIVE LOGITS
     McG
    1.55
    ド
    1.49
     jour
    1.48
     grammar
    1.44
    ppers
    1.42
    McG
    1.39
    umps
    1.38
     Applicant
    1.38
     tricks
    1.36
     schrij
    1.35
    Activations Density 0.005%

    No Known Activations