© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 151297
    Prev
    Next
    INDEX
    Explanations

    legal extent, knowing, silicone, urban, critical

    np_acts-logits-general · gemini-2.5-flash-lite

    longest string prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    health
    0.55
    anov
    0.54
     Summar
    0.52
    shoe
    0.50
    shoes
    0.48
    l
    0.47
    shield
    0.47
     Health
    0.46
    combined
    0.46
     Physicians
    0.46
    POSITIVE LOGITS
    ן
    0.51
     abord
    0.50
    亚
    0.50
    হে
    0.50
    ينية
    0.49
     يصل
    0.49
     يا
    0.49
    ު
    0.49
    يا
    0.48
     выска
    0.47
    Activations Density 0.001%

    No Known Activations