© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10103
    Prev
    Next
    INDEX
    Explanations

    health information, social media, home buying, Kern court, higher education

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

    input validation, heme iron, naming strategies

    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_40_width_16k_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
    ంచరీలు
    0.46
     музе
    0.42
    తులు
    0.42
    த்திலும்
    0.40
    ক্রমে
    0.40
    <unused69>
    0.39
    することで
    0.39
     waarmee
    0.38
    <unused67>
    0.38
    বীন্দ্রনাথ
    0.37
    POSITIVE LOGITS
    に関する
    0.55
    人之
    0.52
    obacterial
    0.52
    észeti
    0.51
    模型的
    0.51
    さんの
    0.50
    வரின்
    0.49
    님의
    0.49
    വരുടെ
    0.49
    வர்களின்
    0.48
    Activations Density 1.090%

    No Known Activations