© 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. 121928
    Prev
    Next
    INDEX
    Explanations

    foreign kids and jobs

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

    through a, those who, sophisticated tools, physical dangers

    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
     లేకుండా
    0.48
     reich
    0.47
     ఇ
    0.47
     voltam
    0.46
     diphenyl
    0.46
    meyer
    0.46
     Became
    0.45
     swore
    0.44
     స్
    0.44
     Wey
    0.44
    POSITIVE LOGITS
    既に
    0.47
    ↵
    0.47
    щё
    0.46
    皆さん
    0.45
    чи
    0.45
    над
    0.44
    querySelectorAll
    0.43
    ন
    0.43
    на
    0.43
    printed
    0.42
    Activations Density 0.000%

    No Known Activations