© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 3035
    Prev
    Next
    INDEX
    Explanations

    ICMP packet

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     रहिए
    0.40
     disponibilités
    0.40
    लाब
    0.39
    डम
    0.38
    われています
    0.36
    స్తుంది
    0.35
    inputSet
    0.34
    จัย
    0.34
    getRedTeam
    0.33
    σ
    0.33
    POSITIVE LOGITS
    满
    0.40
    لیم
    0.40
    Direct
    0.38
    zone
    0.38
     Type
    0.37
    ("")]
    0.37
    Type
    0.36
    hese
    0.34
    bandwidth
    0.34
    Trunc
    0.33
    Activations Density 0.003%

    No Known Activations