© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 15309
    Prev
    Next
    INDEX
    Explanations

    trust and betrayal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_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
     Á
    1.16
     U
    1.14
    U
    1.11
    ios
    1.09
    바로
    1.04
    </h2>
    1.02
     []:
    1.02
    衩
    1.01
     E
    1.00
     Rivers
    0.99
    POSITIVE LOGITS
     betray
    1.08
    erweise
    1.06
     dependability
    1.04
     trusty
    1.04
     trusted
    1.02
     fiduciary
    1.02
    grim
    1.00
     zewnętr
    0.99
    гру
    0.98
    igkeit
    0.96
    Activations Density 0.236%

    No Known Activations