© 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. 54774
    Prev
    Next
    INDEX
    Explanations

    this network, for several

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

    productive environment, Core Progression, space systems

    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
     anomaly
    0.48
     constant
    0.44
     discrete
    0.44
    -
    0.44
     abnormality
    0.43
     input
    0.41
    0.41
    c
    0.41
     خام
    0.41
    ,
    0.41
    POSITIVE LOGITS
    निवेश
    0.54
    ഓം
    0.53
     Oldborough
    0.53
    ৬৫
    0.53
     ተጨማሪ
    0.52
    ສົ່ງ
    0.51
    ⨔
    0.51
     ช่วย
    0.50
    ༘
    0.50
     وتس
    0.49
    Activations Density 0.000%

    No Known Activations