© 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. 17099
    Prev
    Next
    INDEX
    Explanations

    acquisition, town, CEO, leather, fabric

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

    JSON key, particularly younger

    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
     celý
    0.48
     غیر
    0.47
     spying
    0.45
     ㄱ
    0.44
    financing
    0.42
    characterized
    0.41
    zedł
    0.41
    řej
    0.40
     footh
    0.40
     پوری
    0.40
    POSITIVE LOGITS
     getHeight
    0.50
    蚀
    0.49
     способности
    0.47
    いが
    0.44
    んですよね
    0.43
     deserial
    0.43
     опыта
    0.43
     ఆరోగ
    0.43
    т
    0.42
     বাস্তবতা
    0.42
    Activations Density 0.000%

    No Known Activations