© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 168609
    Prev
    Next
    INDEX
    Explanations

    legal advice and review

    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
    ENTY
    0.53
    ITTER
    0.52
     повністю
    0.50
    殼
    0.50
    ΙΑ
    0.50
     sadistic
    0.49
    istatic
    0.49
    ಕರಣ
    0.48
    ATION
    0.47
    ASER
    0.47
    POSITIVE LOGITS
    Biography
    0.45
     Morn
    0.40
    婕
    0.38
    eru
    0.37
     Seats
    0.37
    ವಾರ
    0.37
     blog
    0.36
     tap
    0.36
     ethers
    0.36
     tròn
    0.36
    Activations Density 0.003%

    No Known Activations