© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 144537
    Prev
    Next
    INDEX
    Explanations

    policy agent

    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
    amen
    0.54
    at
    0.54
    ุ
    0.50
    setPreferred
    0.48
    Words
    0.47
    л
    0.47
    ißler
    0.46
    ೇವಿನ
    0.45
    anoia
    0.45
     दम
    0.44
    POSITIVE LOGITS
     absorb
    0.50
     auditory
    0.46
     stets
    0.41
    佛教
    0.41
     unconditionally
    0.41
     eventos
    0.40
     enable
    0.40
     organisms
    0.40
     martial
    0.40
    淆
    0.40
    Activations Density 0.003%

    No Known Activations