© 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. 3053
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    5
    2.08
    3
    2.02
    6
    1.99
    8
    1.89
    ضاء
    1.84
     Mie
    1.82
    7
    1.78
    2
    1.78
    4
    1.78
    Mie
    1.74
    POSITIVE LOGITS
     prospectus
    1.36
     brachte
    1.33
     synopsis
    1.28
    ouncement
    1.20
     marched
    1.19
     portée
    1.18
     Abstracts
    1.17
     slides
    1.16
    囝
    1.15
     threatens
    1.15
    Activations Density 0.147%

    No Known Activations