© 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. 208808
    Prev
    Next
    INDEX
    Explanations

    technical diagrams and specialized terms

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

    lists ending in etc or key

    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
    ロ
    0.46
    SIGNED
    0.45
    h
    0.45
    WriteString
    0.44
    CLOS
    0.44
    ユニット
    0.43
    Metering
    0.43
     বিজ্ঞ
    0.43
    教師
    0.42
    ਰ
    0.42
    POSITIVE LOGITS
     Jehovah
    0.46
     obeying
    0.44
     Muslim
    0.43
     ມີ
    0.43
     Bib
    0.42
     credibility
    0.42
     ď
    0.42
     pioneered
    0.42
     marx
    0.41
     obedience
    0.41
    Activations Density 0.000%

    No Known Activations