© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2002
    Prev
    Next
    INDEX
    Explanations

    war office pixels

    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
    heb
    2.27
    taa
    2.02
     nombreux
    2.01
    ungannya
    1.94
    )}=\
    1.86
    ısına
    1.85
    kwik
    1.85
    estring
    1.85
    こだわ
    1.83
    នៃ
    1.82
    POSITIVE LOGITS
    7
    2.50
    rinsic
    2.44
    InputElement
    2.35
     interfaces
    2.33
    6
    2.29
     ecosystem
    2.26
     ecosystems
    2.25
     Compose
    2.23
     equival
    2.23
     기반
    2.17
    Activations Density 1.060%

    No Known Activations