© 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. 184616
    Prev
    Next
    INDEX
    Explanations

    property details and conditions

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

    humans excel; ensuring Halal

    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
    0.71
    <em>
    0.50
     م
    0.49
    vel
    0.48
    ovel
    0.47
    </u>
    0.46
     storage
    0.46
     mechanistic
    0.46
    pharmac
    0.46
    </h2>
    0.45
    POSITIVE LOGITS
    ૄ
    0.62
    ות
    0.61
    িয়া
    0.54
    দিগের
    0.53
    ંદ્ર
    0.53
    desIP
    0.51
    زی
    0.50
    َى
    0.50
    िनियम
    0.49
    डेजा
    0.49
    Activations Density 0.001%

    No Known Activations