© 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. 29038
    Prev
    Next
    INDEX
    Explanations

    ISSN identifier

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

    daily life activities

    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
    绿
    0.44
     новые
    0.41
     νέα
    0.40
     Green
    0.40
    ุด
    0.40
     ያሉ
    0.39
     великолеп
    0.39
     Promenade
    0.39
     Ян
    0.38
    凉
    0.38
    POSITIVE LOGITS
     proses
    0.54
     process
    0.53
     processus
    0.52
     processo
    0.51
    proses
    0.51
     meestal
    0.51
     आमतौर
    0.50
    process
    0.50
     procesos
    0.50
     процес
    0.48
    Activations Density 0.000%

    No Known Activations