© 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. 62839
    Prev
    Next
    INDEX
    Explanations

    programsorofficial

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

    managing and storing information

    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
    会出现
    0.51
    Complaint
    0.48
     réellement
    0.47
    的问题
    0.47
    读书
    0.46
     mogę
    0.46
    ᒧ
    0.46
    寻
    0.46
    Filename
    0.45
     অপর্ণ
    0.45
    POSITIVE LOGITS
    вся
    0.48
    ozz
    0.47
    0.47
    пред
    0.45
    рус
    0.45
    رس
    0.43
    itih
    0.43
    ри
    0.42
    star
    0.42
    ubs
    0.42
    Activations Density 0.000%

    No Known Activations