© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 112222
    Prev
    Next
    INDEX
    Explanations

    subtle ways, gentle bubbles rising

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
     vasodilator
    0.47
     automóvil
    0.44
    鉀
    0.44
     sensibles
    0.44
     potentiometer
    0.44
     vykon
    0.44
     prêts
    0.44
     signal
    0.43
    وات
    0.43
    البه
    0.43
    POSITIVE LOGITS
    Meng
    0.44
     Isid
    0.43
    జ
    0.43
     Rankings
    0.43
    ж
    0.42
    一看
    0.41
    żs
    0.40
    Justin
    0.40
    під
    0.40
    Andrew
    0.40
    Activations Density 0.001%

    No Known Activations