© 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. 164505
    Prev
    Next
    INDEX
    Explanations

    interferes with memory limit

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

    understand information or concepts

    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
    做法
    0.45
    羔
    0.44
    umen
    0.42
    hed
    0.40
    ére
    0.40
    textfield
    0.39
     scouring
    0.39
    andin
    0.39
    änder
    0.39
    äns
    0.39
    POSITIVE LOGITS
     upravo
    0.50
     enables
    0.50
     swiftly
    0.48
    ത്മ
    0.48
    ۲
    0.48
     grudnia
    0.47
    HW
    0.46
     lengkap
    0.46
    න
    0.45
     surnames
    0.45
    Activations Density 0.000%

    No Known Activations