© 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. 46190
    Prev
    Next
    INDEX
    Explanations

    points per week, capital

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

    explains importance and challenges

    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
     ‫
    0.46
    </strong>
    0.45
    ↵
    0.43
     alerting
    0.43
     Plot
    0.42
     alertness
    0.42
     একাধিক
    0.42
     Greenland
    0.40
     PubMed
    0.40
    undet
    0.40
    POSITIVE LOGITS
    طرف
    0.54
    ZrO
    0.54
    یر
    0.52
     kter
    0.52
    झे
    0.50
     ktore
    0.49
    ሪያ
    0.48
    榫
    0.48
    ্্র
    0.48
    𝐓
    0.48
    Activations Density 0.000%

    No Known Activations