© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4618
    Prev
    Next
    INDEX
    Explanations

    principles, analogy, discord.py, fundamental

    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
    阚
    1.65
     discolor
    1.48
     centerX
    1.45
     discoloration
    1.43
    Bian
    1.39
     monomer
    1.37
     wastes
    1.37
     decommission
    1.36
     electroneg
    1.36
     残
    1.35
    POSITIVE LOGITS
    itação
    0.88
    cita
    0.74
     Corona
    0.73
    inja
    0.72
    onate
    0.72
    ya
    0.71
    真人
    0.71
    платно
    0.69
    astaan
    0.69
    kara
    0.69
    Activations Density 0.039%

    No Known Activations